Professional-Machine-Learning-Engineer Google Professional Machine Learning Engineer Questions and Answers

Vertex AI Model Monitoring is a service that allows you to monitor the performance and quality of your ML models in production. You can use Vertex AI Model Monitoring to detect changes in the input data distribution, the prediction output distribution, or the model accuracy over time. Training-serving skew detection is a feature of Vertex AI Model Monitoring that compares the statistics of the data used for training the model and the data used for serving the model. If there is a significant difference between the two data distributions, it indicates that the model might be outdated or inaccurate. By enabling training-serving skew detection for your model, you can detect model performance changes in production and trigger retraining or redeployment of your model as needed. This way, you can ensure that your model is always up-to-date and accurate, without moving your data to the cloud. References:

Vertex AI Model Monitoring documentation

Training-serving skew detection documentation

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

The best option to build a comprehensive system that recommends images to users that are similar in appearance to their own uploaded images is to download a pretrained convolutional neural network (CNN), and use the model to generate embeddings of the input images. Embeddings are low-dimensional representations of high-dimensional data that capture the essential features and semantics of the data. By using a pretrained CNN, you can leverage the knowledge learned from large-scale image datasets, such as ImageNet, and apply it to your own domain. A pretrained CNN can be used as a feature extractor, where the output of the last hidden layer (or any intermediate layer) is taken as the embedding vector for the input image. You can then measure the similarity between embeddings using a distance metric, such as cosine similarity or Euclidean distance, and recommend images that have the highest similarity scores to the user’s uploaded image. Option A is incorrect because downloading a pretrained CNN and fine-tuning the model to predict hashtags based on the input images may not capture the visual similarity of the images, as hashtags may not reflect the appearance of the images accurately. For example, two images of different breeds of dogs may have the same hashtag #dog, but they may not look similar to each other. Moreover, fine-tuning the model may require additional data and computational resources, and it may not generalize well to new images that have different or missing hashtags. Option B is incorrect because retrieving image labels and dominant colors from the input images using the Vision API may not capture the visual similarity of the images, as labels and colors may not reflect the fine-grained details of the images. For example, two images of the same breed of dog may have different labels and colors depending on the background, lighting, and angle of the image. Moreover, using the Vision API may incur additional costs and latency, and it may not be able to handle custom or domain-specific labels. Option C is incorrect because using the provided hashtags to create a collaborative filtering algorithm may not capture the visual similarity of the images, as collaborative filtering relies on the ratings or preferences of users, not the features of the images. For example, two images of different animals may have similar ratings or preferences from users, but they may not look similar to each other. Moreover, collaborative filtering may suffer from the cold start problem, where new images or users that have no ratings or preferences cannot be recommended. References:

Image similarity search with TensorFlow

Image embeddings documentation

Pretrained models documentation

Similarity metrics documentation

The best option for handling missing values in a categorical feature is to replace them with a placeholder category indicating a missing value. This is a type of imputation, which is a method of estimating the missing values based on the observed data. Imputing the missing values with a placeholder category preserves the information that the data is missing, and avoids introducing bias or distortion in the feature distribution. It also allows the machine learning model to learn from the missingness pattern, and potentially use it as a predictor for the target variable. The other options are not suitable for handling missing values in a categorical feature, because:

Removing the rows with missing values and upsampling the dataset by 5% would reduce the size of the dataset and potentially lose important information. It would also introduce sampling bias and overfitting, as the upsampling process would create duplicate or synthetic observations that do not reflect the true population.

Replacing the missing values with the feature’s mean would not make sense for a categorical feature, as the mean is a numerical measure that does not capture the mode or frequency of the categories. It would also create a new category that does not exist in the original data, and might confuse the machine learning model.

Moving the rows with missing values to the validation dataset would compromise the validity and reliability of the model evaluation, as the validation dataset would not be representative of the test or production data. It would also reduce the amount of data available for training the model, and might introduce leakage or inconsistency between the training and validation datasets. References:

Imputation of missing values

Effective Strategies to Handle Missing Values in Data Analysis

How to Handle Missing Values of Categorical Variables?

Google Cloud launches machine learning engineer certification

Google Professional Machine Learning Engineer Certification

Professional ML Engineer Exam Guide

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Oscillation in the loss during batch training of a neural network means that the model is overshooting the optimal point of the loss function and bouncing back and forth. This can prevent the model from converging to the minimum loss value. One of the main reasons for this phenomenon is that the learning rate hyperparameter, which controls the size of the steps that the model takes along the gradient, is too high. Therefore, decreasing the learning rate hyperparameter can help the model take smaller and more precise steps and avoid oscillation. This is a common technique to improve the stability and performance of neural network training12.

References:

Interpreting Loss Curves

Is learning rate the only reason for training loss oscillation after few epochs?

The best option for implementing a batch inference ML pipeline in Google Cloud, using a model that was developed using TensorFlow and is stored in SavedModel format in Cloud Storage, and a historical dataset containing 10 TB of data that is stored in a BigQuery table, is to configure a Vertex AI batch prediction job to apply the model to the historical data in BigQuery. This option allows you to leverage the power and simplicity of Vertex AI and BigQuery to perform large-scale batch inference with minimal code and configuration. Vertex AI is a unified platform for building and deploying machine learning solutions on Google Cloud. Vertex AI can run a batch prediction job, which can generate predictions for a large number of instances in batches. Vertex AI can also provide various tools and services for data analysis, model development, model deployment, model monitoring, and model governance. A batch prediction job is a resource that can run your model code on Vertex AI. A batch prediction job can help you generate predictions for a large number of instances in batches, and store the prediction results in a destination of your choice. A batch prediction job can accept various input formats, such as JSON, CSV, or TFRecord. A batch prediction job can also accept various input sources, such as Cloud Storage or BigQuery. A TensorFlow model is a resource that represents a machine learning model that is built using TensorFlow. TensorFlow is a framework that can perform large-scale data processing and machine learning. TensorFlow can help you build and train various types of models, such as linear regression, logistic regression, k-means clustering, matrix factorization, and deep neural networks. A SavedModel format is a type of format that can store a TensorFlow model and its associated assets. A SavedModel format can help you save and load your TensorFlow model, and serve it for prediction. A SavedModel format can be stored in Cloud Storage, which is a service that can store and access large-scale data on Google Cloud. A historical dataset is a collection of data that contains historical information about a certain domain. A historical dataset can help you analyze the past trends and patterns of the data, and make predictions for the future. A historical dataset can be stored in BigQuery, which is a service that can store and query large-scale data on Google Cloud. BigQuery can help you analyze your data by using SQL queries, and perform various tasks, such as data exploration, data transformation, or data visualization. By configuring a Vertex AI batch prediction job to apply the model to the historical data in BigQuery, you can implement a batch inference ML pipeline in Google Cloud with minimal code and configuration. You can use the Vertex AI API or the gcloud command-line tool to configure a batch prediction job, and provide the model name, the model version, the input source, the input format, the output destination, and the output format. Vertex AI will automatically run the batch prediction job, and apply the model to the historical data in BigQuery. Vertex AI will also store the prediction results in a destination of your choice, such as Cloud Storage or BigQuery1.

The other options are not as good as option D, for the following reasons:

Option A: Exporting the historical data to Cloud Storage in Avro format, configuring a Vertex AI batch prediction job to generate predictions for the exported data would require more skills and steps than configuring a Vertex AI batch prediction job to apply the model to the historical data in BigQuery, and could increase the complexity and cost of the batch inference process. Avro is a type of format that can store and serialize data in a binary format. Avro can help you compress and encode your data, and support schema evolution and compatibility. By exporting the historical data to Cloud Storage in Avro format, configuring a Vertex AI batch prediction job to generate predictions for the exported data, you can perform batch inference with minimal code and configuration. You can use the BigQuery API or the bq command-line tool to export the historical data to Cloud Storage in Avro format, and use the Vertex AI API or the gcloud command-line tool to configure a batch prediction job, and provide the model name, the model version, the input source, the input format, the output destination, and the output format. However, exporting the historical data to Cloud Storage in Avro format, configuring a Vertex AI batch prediction job to generate predictions for the exported data would require more skills and steps than configuring a Vertex AI batch prediction job to apply the model to the historical data in BigQuery, and could increase the complexity and cost of the batch inference process. You would need to write code, export the historical data to Cloud Storage, configure a batch prediction job, and generate predictions for the exported data. Moreover, this option would not use BigQuery as the input source for the batch prediction job, which can simplify the batch inference process, and provide various benefits, such as fast query performance, serverless scaling, and cost optimization2.

Option B: Importing the TensorFlow model by using the create model statement in BigQuery ML, applying the historical data to the TensorFlow model would not allow you to use Vertex AI to run the batch prediction job, and could increase the complexity and cost of the batch inference process. BigQuery ML is a feature of BigQuery that can create and execute machine learning models in BigQuery by using SQL queries. BigQuery ML can help you build and train various types of models, such as linear regression, logistic regression, k-means clustering, matrix factorization, and deep neural networks. A create model statement is a type of SQL statement that can create a machine learning model in BigQuery ML. A create model statement can help you specify the model name, the model type, the model options, and the model query. By importing the TensorFlow model by using the create model statement in BigQuery ML, applying the historical data to the TensorFlow model, you can perform batch inference with minimal code and configuration. You can use the BigQuery API or the bq command-line tool to import the TensorFlow model by using the create model statement in BigQuery ML, and provide the model name, the model type, the model options, and the model query. You can also use the BigQuery API or the bq command-line tool to apply the historical data to the TensorFlow model, and provide the model name, the input data, and the output destination. However, importing the TensorFlow model by using the create model statement in BigQuery ML, applying the historical data to the TensorFlow model would not allow you to use Vertex AI to run the batch prediction job, and could increase the complexity and cost of the batch inference process. You would need to write code, import the TensorFlow model, apply the historical data, and generate predictions. Moreover, this option would not use Vertex AI, which is a unified platform for building and deploying machine learning solutions on Google Cloud, and provide various tools and services for data analysis, model development, model deployment, model monitoring, and model governance3.

Option C: Exporting the historical data to Cloud Storage in CSV format, configuring a Vertex AI batch prediction job to generate predictions for the exported data would require more skills and steps than configuring a Vertex AI batch prediction job to apply the model to the historical data in BigQuery, and could increase the complexity and cost of the batch inference process. CSV is a type of format that can store and serialize data in a comma-separated values format. CSV can help you store and exchange your data, and support various data types and formats. By exporting the historical data to Cloud Storage in CSV format, configuring a Vertex AI batch prediction job to generate predictions for the exported data, you can perform batch inference with minimal code and configuration. You can use the BigQuery API or the bq command-line tool to export the historical data to Cloud Storage in CSV format, and use the Vertex AI API or the gcloud command-line tool to configure a batch prediction job, and provide the model name, the model version, the input source, the input format, the output destination, and the output format. However, exporting the historical data to Cloud Storage in CSV format, configuring a Vertex AI batch prediction job to generate predictions for the exported data would require more skills and steps than configuring a Vertex AI batch prediction job to apply the model to the historical data in BigQuery, and could increase the complexity and cost of the batch inference process. You would need to write code, export the historical data to Cloud Storage, configure a batch prediction job, and generate predictions for the exported data. Moreover, this option would not use BigQuery as the input source for the batch prediction job, which can simplify the batch inference process, and provide various benefits, such as fast query performance, serverless scaling, and cost optimization2.

References:

Batch prediction | Vertex AI | Google Cloud

Exporting table data | BigQuery | Google Cloud

Creating and using models | BigQuery ML | Google Cloud

 A predict request is a way to send data to a trained model and get predictions in return. A predict request can be written in different formats, such as JSON, protobuf, or gRPC, depending on the service and the platform that are used to host and serve the model. A predict request usually contains the following information:

The signature name: This is the name of the signature that defines the inputs and outputs of the model. A signature is a way to specify the expected format, type, and shape of the data that the model can accept and produce. A signature can be specified when exporting or saving the model, or it can be automatically inferred by the service or the platform. A model can have multiple signatures, but only one can be used for each predict request.

The instances: This is the data that is sent to the model for prediction. The instances can be a single instance or a batch of instances, depending on the size and shape of the data. The instances should match the input specification of the signature, such as the number, name, and type of the input tensors.

For the use case of training a text classification model, the correct way to write the predict request is D. data = json.dumps({“signature_name”: “serving_default”, “instances”: [[‘a’, ‘b’], [‘c’, ‘d’], [‘e’, ‘f’]]})

This option involves writing the predict request in JSON format, which is a common and convenient format for sending and receiving data over the web. JSON stands for JavaScript Object Notation, and it is a way to represent data as a collection of name-value pairs or an ordered list of values. JSON can be easily converted to and from Python objects using the json module.

This option also involves using the signature name “serving_default”, which is the default signature name that is assigned to the model when it is saved or exported without specifying a custom signature name. The serving_default signature defines the input and output tensors of the model based on the SignatureDef that is shown in the image. According to the SignatureDef, the model expects an input tensor called “text” that has a shape of (-1, 2) and a type of DT_STRING, and produces an output tensor called “softmax” that has a shape of (-1, 2) and a type of DT_FLOAT. The -1 in the shape indicates that the dimension can vary depending on the number of instances, and the 2 indicates that the dimension is fixed at 2. The DT_STRING and DT_FLOAT indicate that the data type is string and float, respectively.

This option also involves sending a batch of three instances to the model for prediction. Each instance is a list of two strings, such as [‘a’, ‘b’], [‘c’, ‘d’], or [‘e’, ‘f’]. These instances match the input specification of the signature, as they have a shape of (3, 2) and a type of string. The model will process these instances and produce a batch of three predictions, each with a softmax output that has a shape of (1, 2) and a type of float. The softmax output is a probability distribution over the two possible classes that the model can predict, such as positive or negative sentiment.

Therefore, writing the predict request as data = json.dumps({“signature_name”: “serving_default”, “instances”: [[‘a’, ‘b’], [‘c’, ‘d’], [‘e’, ‘f’]]}) is the correct and valid way to send data to the text classification model and get predictions in return.

References:

[json — JSON encoder and decoder]

 The main advantage of implementing machine learning for this business case is that new problematic phrases can be identified in spam posts. This is because machine learning can learn from the data and the feedback, and adapt to the changing patterns and trends of spam posts. Machine learning can also capture the semantic and contextual meaning of the posts, and not just rely on the presence or absence of keywords. By using machine learning, you can improve the accuracy and coverage of your anti-spam service, and detect new and emerging types of spam posts that may not be captured by the keyword list.

The other options are not advantages of implementing machine learning for this business case for the following reasons:

A. Posts can be compared to the keyword list much more quickly is not an advantage, as it does not improve the quality or effectiveness of the anti-spam service. It only improves the efficiency of the service, which is not the primary objective. Moreover, machine learning may not necessarily be faster than the keyword list, depending on the complexity and size of the model and the data.

C. A much longer keyword list can be used to flag spam posts is not an advantage, as it does not address the limitations or challenges of the keyword list approach. It only increases the size and complexity of the keyword list, which can make it harder to maintain and update. Moreover, a longer keyword list may not improve the accuracy or coverage of the anti-spam service, as it may introduce more false positives or false negatives, or miss new and emerging types of spam posts.

D. Spam posts can be flagged using far fewer keywords is not an advantage, as it does not reflect the capabilities or benefits of machine learning. It only reduces the size and complexity of the keyword list, which can make it easier to maintain and update. However, using fewer keywords may not improve the accuracy or coverage of the anti-spam service, as it may lose some information or meaning of the posts, or miss some types of spam posts.

References:

Professional ML Engineer Exam Guide

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Google Cloud launches machine learning engineer certification

Machine Learning for Spam Detection

Spam Detection Using Machine Learning

 The tf.data dataset is a TensorFlow API that provides a way to create and manipulate data pipelines for machine learning. The tf.data dataset allows you to apply various transformations to the data, such as reading, shuffling, batching, prefetching, and interleaving. These transformations can affect the performance and efficiency of the model training process1

One of the common performance issues in model training is input-bound, which means that the model is waiting for the input data to be ready and is not fully utilizing the computational resources. Input-bound can be caused by slow data loading, insufficient parallelism, or large data size. Input-bound can be detected by using the Cloud TPU profiler plugin, which is a tool that helps you analyze the performance of your model on Cloud TPUs. The Cloud TPU profiler plugin can show you the percentage of time that the TPU cores are idle, which indicates input-bound2

To reduce the input-bound bottleneck and speed up the model training process, you can make some modifications to the tf.data dataset. Two of the modifications that can help are:

Use the interleave option for reading data. The interleave option allows you to read data from multiple files in parallel and interleave their records. This can improve the data loading speed and reduce the idle time of the TPU cores. The interleave option can be applied by using the tf.data.Dataset.interleave method, which takes a function that returns a dataset for each input element, and a number of parallel calls3

Set the prefetch option equal to the training batch size. The prefetch option allows you to prefetch the next batch of data while the current batch is being processed by the model. This can reduce the latency between batches and improve the throughput of the model training. The prefetch option can be applied by using the tf.data.Dataset.prefetch method, which takes a buffer size argument. The buffer size should be equal to the training batch size, which is the number of examples per batch4

The other options are not effective or counterproductive. Reducing the value of the repeat parameter will reduce the number of epochs, which is the number of times the model sees the entire dataset. This can affect the model’s accuracy and convergence. Increasing the buffer size for the shuffle option will increase the randomness of the data, but also increase the memory usage and the data loading time. Decreasing the batch size argument in your transformation will reduce the number of examples per batch, which can affect the model’s stability and performance.

References: 1: tf.data: Build TensorFlow input pipelines 2: Cloud TPU Tools in TensorBoard 3: tf.data.Dataset.interleave 4: tf.data.Dataset.prefetch : [Better performance with the tf.data API]

 Using bfloat16 instead of float32 can reduce the memory usage and training time of the model, while having minimal impact on the accuracy. Bfloat16 is a 16-bit floating-point format that preserves the range of 32-bit floating-point numbers, but reduces the precision from 24 bits to 8 bits. This means that bfloat16 can store the same magnitude of numbers as float32, but with less detail. Bfloat16 is supported by TPUs and some GPUs, and can be used as a drop-in replacement for float32 in most cases. Bfloat16 can also improve the numerical stability of the model, as it reduces the risk of overflow and underflow errors.

Reducing the global batch size, the number of layers, or the dimensions of the images can also reduce the memory usage and training time of the model, but they can also affect the model’s accuracy and performance. Reducing the global batch size can make the model less stable and converge slower, as it reduces the amount of information available for each gradient update. Reducing the number of layers can make the model less expressive and powerful, as it reduces the depth and complexity of the network. Reducing the dimensions of the images can make the model less accurate and robust, as it reduces the resolution and quality of the input data. References:

Bfloat16: The secret to high performance on Cloud TPUs

Bfloat16 floating-point format

How does Batch Size impact your model learning

Recall is the ratio of true positives to the sum of true positives and false negatives. It measures how well the model can identify all the relevant cases. In this scenario, the relevant cases are the pictures that do not meet the profile photo requirements. Therefore, minimizing false negatives means minimizing the cases where the model incorrectly predicts that a non-compliant picture meets the requirements. By using AutoML to optimize the model’s recall, the model will be more likely to reject a non-compliant picture and inform the user accordingly. References:

[AutoML Vision] is a service that allows you to train custom ML models for image classification and object detection tasks. You can use AutoML to optimize your model for different metrics, such as recall, precision, or F1 score.

[Recall] is one of the evaluation metrics for ML models. It is defined as TP / (TP + FN), where TP is the number of true positives and FN is the number of false negatives. Recall measures how well the model can identify all the relevant cases. A high recall means that the model has a low rate of false negatives.

 Image classification is a task where the model assigns a label to an image based on its content, such as “stop sign” or "speed limit"1. Object detection is a task where the model locates and identifies multiple objects in an image, and draws bounding boxes around them2. Since your dataset consists of images that were cropped to show one out of ten different traffic signs, you are dealing with an image classification problem, not an object detection problem. Therefore, you need to train a model for image classification, not object detection.

Vertex AI AutoML is a service that allows you to train and deploy high-quality ML models with minimal effort and machine learning expertise3. You can use Vertex AI AutoML to train a model for image classification by uploading your images and labels to a Vertex AI dataset, and then launching an AutoML training job4. However, Vertex AI AutoML does not allow you to tune the model during each training run, as it automatically selects the best model architecture and hyperparameters for your data4.

Vertex AI custom training is a service that allows you to train and deploy your own custom ML models using your own code and frameworks5. You can use Vertex AI custom training to train a model for image classification by writing your own model training code, such as using TensorFlow or PyTorch, and then creating and running a custom training job. Vertex AI custom training allows you to tune the model during each training run, as you can specify the model architecture and hyperparameters in your code, and use Vertex AI Hyperparameter Tuning to optimize them .

Therefore, the best option for your scenario is to develop the model training code for image classification and train a model by using Vertex AI custom training.

References:

Image classification | TensorFlow Core

Object detection | TensorFlow Core

Introduction to Vertex AI AutoML | Google Cloud

AutoML Vision | Google Cloud

Introduction to Vertex AI custom training | Google Cloud

[Custom training with TensorFlow | Vertex AI | Google Cloud]

[Hyperparameter tuning overview | Vertex AI | Google Cloud]

The best option for resolving the training-serving skew alert is to update the model monitoring job to use the more recent training data that was used to retrain the model. This option can help align the baseline distribution of the model monitoring job with the current distribution of the production data, and eliminate the false positive alerts. Model Monitoring is a service that can track and compare the results of multiple machine learning runs. Model Monitoring can monitor the model’s prediction input data for feature skew and drift. Training-serving skew occurs when the feature data distribution in production deviates from the feature data distribution used to train the model. If the original training data is available, you can enable skew detection to monitor your models for training-serving skew. Model Monitoring uses TensorFlow Data Validation (TFDV) to calculate the distributions and distance scores for each feature, and compares them with a baseline distribution. The baseline distribution is the statistical distribution of the feature’s values in the training data. If the distance score for a feature exceeds an alerting threshold that you set, Model Monitoring sends you an email alert. However, if you retrain the model with more recent training data, and deploy it back to the Vertex AI endpoint, the baseline distribution of the model monitoring job may become outdated and inconsistent with the current distribution of the production data. This can cause the model monitoring job to generate false positive alerts, even if the model performance is not deteriorated. To avoid this problem, you need to update the model monitoring job to use the more recent training data that was used to retrain the model. This can help the model monitoring job to recalculate the baseline distribution and the distance scores, and compare them with the current distribution of the production data. This can also help the model monitoring job to detect any true positive alerts, such as a sudden change in the production data that causes the model performance to degrade1.

The other options are not as good as option B, for the following reasons:

Option A: Updating the model monitoring job to use a lower sampling rate would not resolve the training-serving skew alert, and could reduce the accuracy and reliability of the model monitoring job. The sampling rate is a parameter that determines the percentage of prediction requests that are logged and analyzed by the model monitoring job. Using a lower sampling rate can reduce the storage and computation costs of the model monitoring job, but also the quality and validity of the data. Using a lower sampling rate can introduce sampling bias and noise into the data, and make the model monitoring job miss some important features or patterns of the data. Moreover, using a lower sampling rate would not address the root cause of the training-serving skew alert, which is the mismatch between the baseline distribution and the current distribution of the production data2.

Option C: Temporarily disabling the alert, and enabling the alert again after a sufficient amount of new production traffic has passed through the Vertex AI endpoint, would not resolve the training-serving skew alert, and could expose the model to potential risks and errors. Disabling the alert would stop the model monitoring job from sending email notifications when the distance score for a feature exceeds the alerting threshold, but it would not stop the model monitoring job from calculating and comparing the distributions and distance scores. Therefore, disabling the alert would not address the root cause of the training-serving skew alert, which is the mismatch between the baseline distribution and the current distribution of the production data. Moreover, disabling the alert would prevent the model monitoring job from detecting any true positive alerts, such as a sudden change in the production data that causes the model performance to degrade. This can expose the model to potential risks and errors, and affect the user satisfaction and trust1.

Option D: Temporarily disabling the alert until the model can be retrained again on newer training data, and retraining the model again after a sufficient amount of new production traffic has passed through the Vertex AI endpoint, would not resolve the training-serving skew alert, and could cause unnecessary costs and efforts. Disabling the alert would stop the model monitoring job from sending email notifications when the distance score for a feature exceeds the alerting threshold, but it would not stop the model monitoring job from calculating and comparing the distributions and distance scores. Therefore, disabling the alert would not address the root cause of the training-serving skew alert, which is the mismatch between the baseline distribution and the current distribution of the production data. Moreover, disabling the alert would prevent the model monitoring job from detecting any true positive alerts, such as a sudden change in the production data that causes the model performance to degrade. This can expose the model to potential risks and errors, and affect the user satisfaction and trust. Retraining the model again on newer training data would create a new model version, but it would not update the model monitoring job to use the newer training data as the baseline distribution. Therefore, retraining the model again on newer training data would not resolve the training-serving skew alert, and could cause unnecessary costs and efforts1.

References:

Preparing for Google Cloud Certification: Machine Learning Engineer, Course 3: Production ML Systems, Week 4: Evaluation

Google Cloud Professional Machine Learning Engineer Exam Guide, Section 3: Scaling ML models in production, 3.3 Monitoring ML models in production

Official Google Cloud Certified Professional Machine Learning Engineer Study Guide, Chapter 6: Production ML Systems, Section 6.3: Monitoring ML Models

Using Model Monitoring

Understanding the score threshold slider

Sampling rate

When you deploy a custom container to Vertex AI Model Registry, you need to follow some requirements for the container configuration. One of these requirements is to use the HTTP port 8080 for serving predictions. If you use a different port, the model server might not be able to communicate with Vertex AI and cause the error “Error model server never became ready”. To fix this error, you need to change the HTTP port in your model’s configuration to the default value of 8080 and redeploy the container. References:

Custom container requirements documentation

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

 The Cloud DLP API is a service that allows users to inspect, classify, and de-identify sensitive data. It can be used to scan data in Cloud Storage, BigQuery, Cloud Datastore, and Cloud Pub/Sub. The best way to ensure that the PII is not accessible by unauthorized individuals is to use a quarantine bucket to store the data before scanning it with the DLP API. This way, the data is isolated from other applications and users until it is classified and moved to the appropriate bucket. The other options are not as secure or efficient, as they either expose the data to BigQuery before scanning, or scan the data after writing it to a non-sensitive bucket. References:

Cloud DLP documentation

Scanning and classifying Cloud Storage files

Fine-tuning the model with a company-specific dataset aligns the model outputs with the brand voice, making it better suited for the company's objectives. Adjusting the temperature (Option A) affects randomness rather than content style, and changing token limits (Option C) does not impact tone. Replacing the model (Option D) is inefficient without guarantees of better alignment.

 BigQuery ML allows you to build and run machine learning models using SQL queries directly within BigQuery, which is one of the simplest approaches because it doesn't require setting up an external environment like Vertex AI or managing infrastructure.

 AutoML regression is more appropriate for predicting customer lifetime value (CLV) compared to ARIMA, which is typically used for time series forecasting (e.g., sales over time, stock prices, etc.). CLV prediction involves understanding complex relationships between customer behavior and value, which is best captured by a regression model.

 Using BigQuery Studio and running a CREATE MODEL statement to build an AutoML regression model offers the simplicity you're looking for because it automates much of the feature engineering, model selection, and hyperparameter tuning.

 The other options involving ARIMA models (A and B) are not appropriate for CLV, and setting up a Vertex AI Workbench notebook (D) introduces unnecessary complexity for this task.

You are implementing a batch inference ML pipeline in Google Cloud. The model was developed by using TensorFlow and is stored in SavedModel format in Cloud Storage. You need to apply the model to a historical dataset that is stored in a BigQuery table. You want to perform inference with minimal effort. What should you do?

A. Import the TensorFlow model by using the create model statement in BigQuery ML. Apply the historical data to the TensorFlow model.

B. Export the historical data to Cloud Storage in Avro format. Configure a Vertex Al batch prediction job to generate predictions for the exported data.

C. Export the historical data to Cloud Storage in CSV format. Configure a Vertex Al batch prediction job to generate predictions for the exported data.

D. Configure and deploy a Vertex Al endpoint. Use the endpoint to get predictions from the historical data in BigQuery.

Answer: B

 Vertex AI batch prediction is the most appropriate and efficient way to apply a pre-trained model like TensorFlow’s SavedModel to a large dataset, especially for batch processing.

 The Vertex AI batch prediction job works by exporting your dataset (in this case, historical data from BigQuery) to a suitable format (like Avro or CSV) and then processing it in Cloud Storage where the model is stored.

 Avro format is recommended for large datasets as it is highly efficient for data storage and is optimized for read/write operations in Google Cloud, which is why option B is correct.

 Option A suggests using BigQuery ML for inference, but it does not support running arbitrary TensorFlow models directly within BigQuery ML. Hence, BigQuery ML is not a valid option for this particular task.

 Option C (exporting to CSV) is a valid alternative but is less efficient compared to Avro in terms of performance.

 Option D suggests deploying a Vertex AI endpoint, which is better suited for real-time inference rather than batch inference. Since the question asks for batch inference, B is the best answer.

Option A is not the best answer because it requires storing the pickled model in Cloud Storage, which may incur additional cost and latency for loading the model. It also requires building a Flask-based app, which may not be necessary for a simple data preprocessing step.

Option B is not the best answer because it requires building a Flask-based app, which may not be necessary for a simple data preprocessing step. It also requires packaging the app and the pickled model in a custom container image, which may increase the size and complexity of the image.

Option C is not the best answer because it requires packaging the pickled model in a custom container image, which may increase the size and complexity of the image. It also does not leverage the Vertex built-in container image, which may provide some optimizations and integrations for XGBoost models.

Option D is the best answer because it leverages the Vertex built-in container image, which may provide some optimizations and integrations for XGBoost models. It also allows storing the pickled model in Cloud Storage, which may reduce the size and complexity of the image. It also allows building a custom predictor class based on XGBoost Predictor from the Vertex AI SDK, which may simplify the data preprocessing step and the prediction logic.

The best option for using Vertex AI Model Monitoring for drift detection and minimizing the cost is to use the features and the feature attributions for monitoring, and set a prediction-sampling-rate value that is closer to 0 than 1. This option allows you to leverage the power and flexibility of Google Cloud to detect feature drift in the input predict requests for custom models, and reduce the storage and computation costs of the model monitoring job. Vertex AI Model Monitoring is a service that can track and compare the results of multiple machine learning runs. Vertex AI Model Monitoring can monitor the model’s prediction input data for feature skew and drift. Feature drift occurs when the feature data distribution in production changes over time. If the original training data is not available, you can enable drift detection to monitor your models for feature drift. Vertex AI Model Monitoring uses TensorFlow Data Validation (TFDV) to calculate the distributions and distance scores for each feature, and compares them with a baseline distribution. The baseline distribution is the statistical distribution of the feature’s values in the training data. If the training data is not available, the baseline distribution is calculated from the first 1000 prediction requests that the model receives. If the distance score for a feature exceeds an alerting threshold that you set, Vertex AI Model Monitoring sends you an email alert. However, if you use a custom model, you can also enable feature attribution monitoring, which can provide more insights into the feature drift. Feature attribution monitoring analyzes the feature attributions, which are the contributions of each feature to the prediction output. Feature attribution monitoring can help you identify the features that have the most impact on the model performance, and the features that have the most significant drift over time. Feature attribution monitoring can also help you understand the relationship between the features and the prediction output, and the correlation between the features1. The prediction-sampling-rate is a parameter that determines the percentage of prediction requests that are logged and analyzed by the model monitoring job. Using a lower prediction-sampling-rate can reduce the storage and computation costs of the model monitoring job, but also the quality and validity of the data. Using a lower prediction-sampling-rate can introduce sampling bias and noise into the data, and make the model monitoring job miss some important features or patterns of the data. However, using a higher prediction-sampling-rate can increase the storage and computation costs of the model monitoring job, and also the amount of data that needs to be processed and analyzed. Therefore, there is a trade-off between the prediction-sampling-rate and the cost and accuracy of the model monitoring job, and the optimal prediction-sampling-rate depends on the business objective and the data characteristics2. By using the features and the feature attributions for monitoring, and setting a prediction-sampling-rate value that is closer to 0 than 1, you can use Vertex AI Model Monitoring for drift detection and minimize the cost.

The other options are not as good as option D, for the following reasons:

Option A: Using the features for monitoring and setting a monitoring-frequency value that is higher than the default would not enable feature attribution monitoring, and could increase the cost of the model monitoring job. The monitoring-frequency is a parameter that determines how often the model monitoring job analyzes the logged prediction requests and calculates the distributions and distance scores for each feature. Using a higher monitoring-frequency can increase the frequency and timeliness of the model monitoring job, but also the computation costs of the model monitoring job. Moreover, using the features for monitoring would not enable feature attribution monitoring, which can provide more insights into the feature drift and the model performance1.

Option B: Using the features for monitoring and setting a prediction-sampling-rate value that is closer to 1 than 0 would not enable feature attribution monitoring, and could increase the cost of the model monitoring job. The prediction-sampling-rate is a parameter that determines the percentage of prediction requests that are logged and analyzed by the model monitoring job. Using a higher prediction-sampling-rate can increase the quality and validity of the data, but also the storage and computation costs of the model monitoring job. Moreover, using the features for monitoring would not enable feature attribution monitoring, which can provide more insights into the feature drift and the model performance12.

Option C: Using the features and the feature attributions for monitoring and setting a monitoring-frequency value that is lower than the default would enable feature attribution monitoring, but could reduce the frequency and timeliness of the model monitoring job. The monitoring-frequency is a parameter that determines how often the model monitoring job analyzes the logged prediction requests and calculates the distributions and distance scores for each feature. Using a lower monitoring-frequency can reduce the computation costs of the model monitoring job, but also the frequency and timeliness of the model monitoring job. This can make the model monitoring job less responsive and effective in detecting and alerting the feature drift1.

References:

Preparing for Google Cloud Certification: Machine Learning Engineer, Course 3: Production ML Systems, Week 4: Evaluation

Google Cloud Professional Machine Learning Engineer Exam Guide, Section 3: Scaling ML models in production, 3.3 Monitoring ML models in production

Official Google Cloud Certified Professional Machine Learning Engineer Study Guide, Chapter 6: Production ML Systems, Section 6.3: Monitoring ML Models

Using Model Monitoring

Understanding the score threshold slider

To create a Vertex AI Workbench environment for your team and limit access to other employees in your project, you should follow these steps:

Create a new service account and grant it the Vertex AI User role. This role grants full access to all resources in Vertex AI, including creating and managing notebook instances1.

Grant the Service Account User role to each team member on the service account. This role allows the team members to impersonate the service account and use its permissions2.

Grant the Notebook Viewer role to each team member. This role allows the team members to view and connect to the notebook instance, but not to modify or delete it3.

Provision a Vertex AI Workbench user-managed notebook instance that uses the new service account. This way, the notebook instance will run as the service account and only the team members who have the Service Account User and Notebook Viewer roles will be able to access it.

References:

1: Vertex AI access control with IAM | Google Cloud

2: Understanding service accounts | Cloud IAM Documentation

3: Manage access to a Vertex AI Workbench instance | Google Cloud

[4]: Create and manage Vertex AI Workbench instances | Google Cloud

Dynamic range quantization is a model optimization technique for reducing latency that reduces the numerical precision of the weights and activations of models. This technique can reduce the model size, memory usage, and inference time by up to 4x with negligible accuracy loss. Dynamic range quantization can be applied to a trained TensorFlow model without retraining, and it is suitable for mobile applications that require low latency and power consumption.

Weight pruning, model distillation, and dimensionality reduction are also model optimization techniques for reducing latency, but they have some limitations or drawbacks compared to dynamic range quantization:

Weight pruning works by removing parameters within a model that have only a minor impact on its predictions. Pruned models are the same size on disk, and have the same runtime latency, but can be compressed more effectively. This makes pruning a useful technique for reducing model download size, but not for reducing inference time.

Model distillation works by training a smaller and simpler model (student) to mimic the behavior of a larger and complex model (teacher). Distilled models can have lower latency and memory usage than the original models, but they require retraining and may not preserve the accuracy of the teacher model.

Dimensionality reduction works by reducing the number of features or dimensions in the input data or the model layers. Dimensionality reduction can improve the computational efficiency and generalization ability of models, but it may also lose some information or introduce noise in the data or the model. Dimensionality reduction also requires retraining or modifying the model architecture.

References:

[TensorFlow Model Optimization]

[TensorFlow Model Optimization Toolkit — Post-Training Integer Quantization]

[Model optimization methods to cut latency, adapt to new data]

 The best option for splitting the data between the training, validation, and test sets, using a managed tabular dataset in Vertex AI that contains sales data from three different stores, is to use Vertex AI default data split. This option allows you to leverage the power and simplicity of Vertex AI to automatically and randomly split your data into the three sets by percentage. Vertex AI is a unified platform for building and deploying machine learning solutions on Google Cloud. Vertex AI can support various types of models, such as linear regression, logistic regression, k-means clustering, matrix factorization, and deep neural networks. Vertex AI can also provide various tools and services for data analysis, model development, model deployment, model monitoring, and model governance. A default data split is a data split method that is provided by Vertex AI, and does not require any user input or configuration. A default data split can help you split your data into the training, validation, and test sets by using a random sampling method, and assign a fixed percentage of the data to each set. A default data split can help you simplify the data split process, and works well in most cases. A training set is a subset of the data that is used to train the model, and adjust the model parameters. A training set can help you learn the relationship between the input features and the target variable, and optimize the model performance. A validation set is a subset of the data that is used to validate the model, and tune the model hyperparameters. A validation set can help you evaluate the model performance on unseen data, and avoid overfitting or underfitting. A test set is a subset of the data that is used to test the model, and provide the final evaluation metrics. A test set can help you assess the model performance on new data, and measure the generalization ability of the model. By using Vertex AI default data split, you can split your data into the training, validation, and test sets by using a random sampling method, and assign the following percentages of the data to each set1:

The other options are not as good as option B, for the following reasons:

Option A: Using Vertex AI manual split, using the store name feature to assign one store for each set would not allow you to split your data into representative and balanced sets, and could cause errors or poor performance. A manual split is a data split method that allows you to control how your data is split into sets, by using the ml_use label or the data filter expression. A manual split can help you customize the data split logic, and handle complex or non-standard data formats. A store name feature is a feature that indicates the name of the store where the sales data was collected. A store name feature can help you identify the source of the data, and group the data by store. However, using Vertex AI manual split, using the store name feature to assign one store for each set would not allow you to split your data into representative and balanced sets, and could cause errors or poor performance. You would need to write code, create and configure the ml_use label or the data filter expression, and assign one store for each set. Moreover, this option would not ensure that the data in each set has the same distribution and characteristics as the data in the whole dataset, which could prevent you from learning the general pattern of the data, and cause bias or variance in the model2.

Option C: Using Vertex AI chronological split and specifying the sales timestamp feature as the time variable would not allow you to split your data into representative and balanced sets, and could cause errors or poor performance. A chronological split is a data split method that allows you to split your data into sets based on the order of the data. A chronological split can help you preserve the temporal dependency and sequence of the data, and avoid data leakage. A sales timestamp feature is a feature that indicates the date and time when the sales data was collected. A sales timestamp feature can help you track the changes and trends of the data over time, and capture the seasonality and cyclicality of the data. However, using Vertex AI chronological split and specifying the sales timestamp feature as the time variable would not allow you to split your data into representative and balanced sets, and could cause errors or poor performance. You would need to write code, create and configure the time variable, and split the data by the order of the time variable. Moreover, this option would not ensure that the data in each set has the same distribution and characteristics as the data in the whole dataset, which could prevent you from learning the general pattern of the data, and cause bias or variance in the model3.

Option D: Using Vertex AI random split, assigning 70% of the rows to the training set, 10% to the validation set, and 20% to the test set would not allow you to use the default data split method that is provided by Vertex AI, and could increase the complexity and cost of the data split process. A random split is a data split method that allows you to split your data into sets by using a random sampling method, and assign a custom percentage of the data to each set. A random split can help you split your data into representative and balanced sets, and avoid data leakage. However, using Vertex AI random split, assigning 70% of the rows to the training set, 10% to the validation set, and 20% to the test set would not allow you to use the default data split method that is provided by Vertex AI, and could increase the complexity and cost of the data split process. You would need to write code, create and configure the random split method, and assign the custom percentages to each set. Moreover, this option would not use the default data split method that is provided by Vertex AI, which can simplify the data split process, and works well in most cases1.

References:

About data splits for AutoML models | Vertex AI | Google Cloud

Manual split for unstructured data

Mathematical split

 Overfitting occurs when a model tries to fit the training data so closely that it does not generalize well to new data. Overfitting can be caused by having a model that is too complex for the data, such as having too many parameters or layers. Overfitting can lead to poor performance on the validation data, which reflects how the model will perform on unseen data1

To prevent overfitting, one strategy is to use regularization techniques that penalize the complexity of the model and encourage it to learn simpler patterns. Two common regularization techniques for deep neural networks are L2 regularization and dropout. L2 regularization adds a term to the loss function that is proportional to the squared magnitude of the model’s weights. This term penalizes large weights and encourages the model to use smaller weights. Dropout randomly drops out some units in the network during training, which prevents co-adaptation of features and reduces the effective number of parameters. Both L2 regularization and dropout have hyperparameters that control the strength of the regularization effect23

Another strategy to prevent overfitting is to use hyperparameter tuning, which is the process of finding the optimal values for the parameters of the model that affect its performance. Hyperparameter tuning can help find the best combination of hyperparameters that minimize the validation loss and improve the generalization ability of the model. AI Platform provides a service for hyperparameter tuning that can run multiple trials in parallel and use different search algorithms to find the best solution.

Therefore, the best strategy to use when retraining the model is to run a hyperparameter tuning job on AI Platform to optimize for the L2 regularization and dropout parameters. This will allow the model to find the optimal balance between fitting the training data and generalizing to new data. The other options are not as effective, as they either use fixed values for the regularization parameters, which may not be optimal, or they do not address the issue of overfitting at all.

References: 1: Generalization: Peril of Overfitting 2: Regularization for Deep Learning 3: Dropout: A Simple Way to Prevent Neural Networks from Overfitting : [Hyperparameter tuning overview]

 According to the official exam guide1, one of the skills assessed in the exam is to “explain the predictions of a trained model”. TensorFlow2 is an open source framework for developing and deploying machine learning and deep learning models. TensorFlow supports various model explainability methods, such as Integrated Gradients3, which is a technique that assigns an importance score to each input feature by approximating the integral of the gradients along the path from a baseline input to the actual input. Integrated Gradients can help explain the output of a deep learning-based model by highlighting the most influential features in the input images. Therefore, option C is the best way to build the model for the given use case. The other options are not relevant or optimal for this scenario. References:

Professional ML Engineer Exam Guide

TensorFlow

Integrated Gradients

Google Professional Machine Learning Certification Exam 2023

Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

 BigQuery is a service that allows you to store and query large amounts of data in a scalable and cost-effective way. You can use BigQuery to prepare the data for your customer churn prediction model, such as filtering, aggregating, and transforming the data. You can then associate the data with a Vertex AI dataset, which is a service that allows you to store and manage your ML data on Google Cloud. By using a Vertex AI dataset, you can easily access the data from other Vertex AI services, such as AutoML. AutoML is a service that allows you to create and train ML models without writing code. You can use AutoML to create an AutoMLTabularTrainingJob, which is a type of job that trains a classification model for tabular data, such as customer churn. By using an AutoMLTabularTrainingJob, you can benefit from the automated feature engineering, model selection, and hyperparameter tuning that AutoML provides. You can also use Vertex Explainable AI to understand how your model is making predictions, such as which features are most important and how they affect the prediction outcome. By using BigQuery, Vertex AI dataset, and AutoMLTabularTrainingJob, you can build your first model as quickly as possible while minimizing cost and complexity. References:

BigQuery documentation

Vertex AI dataset documentation

AutoMLTabularTrainingJob documentation

Vertex Explainable AI documentation

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

 In this scenario, the goal is to speed up model training for a CNN-based architecture on Google Cloud. The code does not include any manual device placement and has not been wrapped in Estimator model-level abstraction. Given these constraints, the best environment to train the model on would be a Deep Learning VM with an n1-standard-2 machine and 1 GPU with all libraries pre-installed. Option C is the correct answer.

Option C: A Deep Learning VM with an n1-standard-2 machine and 1 GPU with all libraries pre-installed. This option is the most suitable for the scenario because it provides a ready-to-use environment for deep learning on Google Cloud. A Deep Learning VM is a specialized VM image that is pre-installed with popular deep learning frameworks such as TensorFlow, PyTorch, Keras, and more. A Deep Learning VM also comes with NVIDIA GPU drivers and CUDA libraries that enable GPU acceleration for model training. A Deep Learning VM can be easily configured and launched from the Google Cloud Console or the Cloud SDK. An n1-standard-2 machine is a general-purpose machine type that provides 2 vCPUs and 7.5 GB of memory. This machine type can be sufficient for running a CNN-based architecture. A GPU is a specialized hardware accelerator that can speed up the computation of matrix operations and convolutions, which are common in CNN-based architectures. By using a Deep Learning VM with an n1-standard-2 machine and 1 GPU, the model training can be significantly faster than on an on-premises CPU-only infrastructure.

Option A: A VM on Compute Engine and 1 TPU with all dependencies installed manually. This option is not suitable for the scenario because it requires manual installation of dependencies and device placement. A TPU is a custom-designed ASIC that can provide high performance and efficiency for TensorFlow models. However, to use a TPU, the code needs to include manual device placement and be wrapped in Estimator model-level abstraction. Moreover, to use a TPU, the dependencies such as TensorFlow, Cloud TPU Client, and Cloud Storage need to be installed manually on the VM. This option can be complex and time-consuming to set up and may not be compatible with the existing code.

Option B: A VM on Compute Engine and 8 GPUs with all dependencies installed manually. This option is not suitable for the scenario because it requires manual installation of dependencies and may not be cost-effective. While using 8 GPUs can provide high parallelism and speed for model training, it also increases the cost and complexity of the environment. Moreover, to use GPUs, the dependencies such as NVIDIA GPU drivers, CUDA libraries, and deep learning frameworks need to be installed manually on the VM. This option can be tedious and error-prone to set up and may not be necessary for the scenario.

Option D: A Deep Learning VM with more powerful CPU e2-highcpu-16 machines with all libraries pre-installed. This option is not suitable for the scenario because it does not leverage GPU acceleration for model training. While using more powerful CPU machines can provide more compute resources and memory for model training, it may not be as fast and efficient as using GPU machines. CPU machines are not optimized for matrix operations and convolutions, which are common in CNN-based architectures. Moreover, using more powerful CPU machines can also increase the cost of the environment. This option can be suboptimal and wasteful for the scenario.

References:

Deep Learning VM Image documentation

Compute Engine documentation

Cloud TPU documentation

Machine types documentation

GPUs on Compute Engine documentation

Option A is incorrect because training local surrogate models to explain individual predictions is not a feature of Vertex Explainable AI, but rather a general technique for interpreting black-box models. Local surrogate models are simpler models that approximate the behavior of the original model around a specific input1.

Option B is correct because configuring sampled Shapley explanations on Vertex Explainable AI is a way to explain the difference between the actual prediction and the average prediction for a given input. Sampled Shapley explanations are based on the Shapley value, which is a game-theoretic concept that measures how much each feature contributes to the prediction2. Vertex Explainable AI supports sampled Shapley explanations for tabular data, such as customer churn3.

Option C is incorrect because configuring integrated gradients explanations on Vertex Explainable AI is not suitable for explaining the difference between the actual prediction and the average prediction for a given input. Integrated gradients explanations are based on the idea of computing the gradients of the prediction with respect to the input features along a path from a baseline input to the actual input4. Vertex Explainable AI supports integrated gradients explanations for image and text data, but not for tabular data3.

Option D is incorrect because measuring the effect of each feature as the weight of the feature multiplied by the feature value is not a valid way to explain the difference between the actual prediction and the average prediction for a given input. This method assumes that the model is linear and additive, which is not the case for an ensemble of trees and neural networks. Moreover, this method does not account for the interactions between features or the non-linearity of the model5.

References:

Local surrogate models

Shapley value

Vertex Explainable AI overview

Integrated gradients

Feature importance

 Entity extraction is a natural language processing (NLP) task that involves identifying and extracting specific types of information from text, such as names, dates, locations, etc. Entity extraction can help you analyze a corpus of recipes and extract each ingredient and cookware mentioned in them. Vertex AI is a unified platform for building and managing machine learning solutions on Google Cloud. It provides a service for AutoML entity extraction, which allows you to create and train custom entity extraction models without writing any code. You can use Vertex AI to create a text dataset for entity extraction, and label your data with two entities: “ingredient” and “cookware”. You need to label at least 200 examples of each entity type to train an AutoML entity extraction model. You can also use a holdout dataset to evaluate the performance of your model, such as precision, recall, and F1-score. This solution can help you build a machine learning model to scan a corpus of recipes and extract each ingredient and cookware mentioned in them, and use the results to help users with meal planning. References:

AutoML Entity Extraction | Vertex AI

Preparing data for AutoML Entity Extraction | Vertex AI

TFRecords are a binary file format that can store large amounts of data efficiently. By converting the images to TFRecords and storing them in a Cloud Storage bucket, you can reduce the data size and improve the data transfer speed. You can then read the TFRecords by using the tf.data.TFRecordDataset function, which creates a dataset of tensors from the TFRecord files. This way, you can read images at scale during training while minimizing data I/O bottlenecks. References:

TFRecord documentation

tf.data.TFRecordDataset documentation

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

AutoML Vision Edge is a service that allows you to create custom image classification and object detection models that can run on edge devices, such as mobile phones, tablets, or IoT devices1. AutoML Vision Edge offers four types of models that vary in size, accuracy, and latency: mobile-versatile-1, mobile-low-latency-1, mobile-high-accuracy-1, and mobile-core-ml-low-latency-12. Each model has its own trade-offs and use cases, depending on the device specifications and the application requirements.

For the use case of building an ML model to reduce the amount of time spent by quality control inspectors checking for product defects, the best model to use is the AutoML Vision Edge mobile-low-latency-1 model. This model is optimized for fast inference on mobile devices, with a latency of less than 50 milliseconds on a Pixel 1 phone2. Faster defect detection is a priority for the toy manufacturer, and the factory does not have reliable Wi-Fi, so a low-latency model that can run on the device without internet connection is ideal. The mobile-low-latency-1 model also has a small size of less than 4 MB, which makes it easy to deploy and update2. The mobile-low-latency-1 model has a slightly lower accuracy than the mobile-high-accuracy-1 model, but it is still suitable for most image classification tasks2. Therefore, the AutoML Vision Edge mobile-low-latency-1 model is the best option for this use case.

References:

AutoML Vision Edge documentation

AutoML Vision Edge model types

This answer is correct because it allows you to use the trained TensorFlow model for batch predictions on text data stored in BigQuery without any additional processing or overhead. Al Platform provides a service for running batch prediction jobs that can take input data from BigQuery or Cloud Storage and write the output to BigQuery or Cloud Storage. You can use the SavedModel format to export your TensorFlow model to Cloud Storage and then submit a batch prediction job that points to the model location and the input data location. Al Platform will handle the scaling and distribution of the prediction requests and return the results in the specified output location. References:

[Al Platform: Batch prediction overview]

[Al Platform: Exporting a SavedModel for prediction]

According to the official exam guide1, one of the skills assessed in the exam is to “automate and orchestrate ML pipelines using Cloud Composer”. Vertex AI Pipelines2 is a service that allows you to orchestrate your ML workflows using Kubeflow Pipelines SDK v2 or TensorFlow Extended. Vertex AI Pipelines supports execution caching, which means that if you run a pipeline and it reaches a component that has already been run with the same inputs and parameters, the component does not run again. Instead, the component uses the output from the previous run. This can save you time and resources when you are iterating on your pipeline. Therefore, option A is the best way to reduce model development costs, as it enables execution caching for the data export and preprocessing steps, which are likely to be the same for each model iteration. The other options are not relevant or optimal for this scenario. References:

Professional ML Engineer Exam Guide

Vertex AI Pipelines

Google Professional Machine Learning Certification Exam 2023

Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

The best option for analyzing large and complex datasets while minimizing computational resources is to use a combination of BigQuery and Vertex AI Workbench. BigQuery is a serverless, scalable, and cost-effective data warehouse that can perform fast and interactive queries on petabytes of data. BigQuery can calculate descriptive statistics such as mean, median, and mode by using SQL functions such as AVG, PERCENTILE_CONT, and MODE. Vertex AI Workbench is a managed service that provides an integrated development environment for data science and machine learning. Vertex AI Workbench allows users to create and run Jupyter notebooks on Google Cloud, and access various tools and libraries for data visualization and statistical analysis. Vertex AI Workbench can connect to BigQuery and use the results of the queries to create time plots and run statistical tests for hypothesis testing. By using BigQuery and Vertex AI Workbench, users can leverage the power and flexibility of Google Cloud to perform exploratory data analysis on large and complex datasets. References:

Preparing for Google Cloud Certification: Machine Learning Engineer, Course 2: Data Engineering for ML on Google Cloud, Week 1: Introduction to Data Engineering for ML

Google Cloud Professional Machine Learning Engineer Exam Guide, Section 1: Architecting low-code ML solutions, 1.1 Developing ML models by using BigQuery ML

Official Google Cloud Certified Professional Machine Learning Engineer Study Guide, Chapter 3: Data Engineering for ML, Section 3.2: BigQuery for ML

Dataflow is a fully managed service for executing Apache Beam pipelines that can process streaming or batch data1.

Al Platform is a unified platform that enables you to build and run machine learning applications across Google Cloud2.

BigQuery is a serverless, highly scalable, and cost-effective cloud data warehouse designed for business agility3.

These services are suitable for building an ML model to detect anomalies in real-time sensor data, as they can handle large-scale data ingestion, preprocessing, training, serving, storage, and visualization. The other options are not as suitable because:

DataProc is a service for running Apache Spark and Apache Hadoop clusters, which are not optimized for streaming data processing4.

AutoML is a suite of machine learning products that enables developers with limited machine learning expertise to train high-quality models specific to their business needs5. However, it does not support custom models or real-time predictions.

Cloud Bigtable is a scalable, fully managed NoSQL database service for large analytical and operational workloads. However, it is not designed for ad hoc queries or interactive analysis.

Cloud Functions is a serverless execution environment for building and connecting cloud services. However, it is not suitable for storing or visualizing data.

Cloud Storage is a service for storing and accessing data on Google Cloud. However, it is not a data warehouse and does not support SQL queries or visualization tools.

To log the metrics of a machine learning model in TensorFlow using the Vertex AI Python SDK, you should utilize the aiplatform.log_metrics function to log the F1 score and aiplatform.log_classification_metrics function to log the confusion matrix. These functions allow users to manually record and store evaluation metrics for each model, facilitating an efficient comparison based on specific performance indicators like F1 scores and confusion matrices. References: The answer can be verified from official Google Cloud documentation and resources related to Vertex AI and TensorFlow.

Vertex AI Python SDK reference | Google Cloud

Logging custom metrics | Vertex AI

Migrating from scikit-learn to TensorFlow | TensorFlow

Option A is correct because using local feature importance from the predictions is the best way to provide the reasons that contributed to the model’s decision for a specific customer’s loan request. Local feature importance is a measure of how much each feature affects the prediction for a given instance, relative to the average prediction for the dataset1. AutoML Tables provides local feature importance values for each prediction, which can be accessed using the Vertex AI SDK for Python or the Cloud Console2. By using local feature importance, you can explain why the model rejected the loan request based on the customer’s data.

Option B is incorrect because using the correlation with target values in the data summary page is not a good way to provide the reasons that contributed to the model’s decision for a specific customer’s loan request. The correlation with target values is a measure of how much each feature is linearly related to the target variable for the entire dataset, not for a single instance3. The data summary page in AutoML Tables shows the correlation with target values for each feature, as well as other statistics such as mean, standard deviation, and histogram4. However, these statistics are not useful for explaining the model’s decision for a specific customer, as they do not account for the interactions between features or the non-linearity of the model.

Option C is incorrect because using the feature importance percentages in the model evaluation page is not a good way to provide the reasons that contributed to the model’s decision for a specific customer’s loan request. The feature importance percentages are a measure of how much each feature affects the overall accuracy of the model for the entire dataset, not for a single instance5. The model evaluation page in AutoML Tables shows the feature importance percentages for each feature, as well as other metrics such as precision, recall, and confusion matrix. However, these metrics are not useful for explaining the model’s decision for a specific customer, as they do not reflect the individual contribution of each feature for a given prediction.

Option D is incorrect because varying features independently to identify the threshold per feature that changes the classification is not a feasible way to provide the reasons that contributed to the model’s decision for a specific customer’s loan request. This method involves changing the value of one feature at a time, while keeping the other features constant, and observing how the prediction changes. However, this method is not practical, as it requires making multiple prediction requests, and may not capture the interactions between features or the non-linearity of the model.

References:

Local feature importance

Getting local feature importance values

Correlation with target values

Data summary page

Feature importance percentages

[Model evaluation page]

[Varying features independently]

The best option to ensure that the features with the largest magnitude don’t overfit the model is to normalize the data by scaling it to have values between 0 and 1. This is also known as min-max scaling or feature scaling, and it can reduce the variance and skewness of the data, as well as improve the numerical stability and convergence of the model. Normalizing the data can also make the model less sensitive to the scale of the features, and more focused on the relative importance of each feature. Normalizing the data can be done using various methods, such as dividing each value by the maximum value, subtracting the minimum value and dividing by the range, or using the sklearn.preprocessing.MinMaxScaler function in Python.

The other options are not optimal for the following reasons:

A. Standardizing the data by transforming it with a logarithmic function is not a good option, as it can distort the distribution and relationship of the data, and introduce bias and errors. Moreover, the logarithmic function is not defined for negative or zero values, which can limit its applicability and cause problems for the model.

B. Applying a principal component analysis (PCA) to minimize the effect of any particular feature is not a good option, as it can reduce the interpretability and explainability of the data and the model. PCA is a dimensionality reduction technique that transforms the data into a new set of orthogonal features that capture the most variance in the data. However, these new features are not directly related to the original features, and can lose some information and meaning in the process. Moreover, PCA can be computationally expensive and complex, and may not be necessary for the problem at hand.

C. Using a binning strategy to replace the magnitude of each feature with the appropriate bin number is not a good option, as it can lose the granularity and precision of the data, and introduce noise and outliers. Binning is a discretization technique that groups the continuous values of a feature into a finite number of bins or categories. However, this can reduce the variability and diversity of the data, and create artificial boundaries and gaps that may not reflect the true nature of the data. Moreover, binning can be arbitrary and subjective, and depend on the choice of the bin size and number.

References:

Professional ML Engineer Exam Guide

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Google Cloud launches machine learning engineer certification

Feature Scaling for Machine Learning: Understanding the Difference Between Normalization vs. Standardization

sklearn.preprocessing.MinMaxScaler documentation

Principal Component Analysis Explained Visually

Binning Data in Python

In this scenario, the goal is to create a custom fraud detection model using AutoML Tables. Fraud detection is a type of binary classification problem, where the model needs to predict whether a transaction is fraudulent or not. The optimization objective is a metric that defines how the model is trained and evaluated. AutoML Tables allows you to choose from different optimization objectives for binary classification problems, such as Log loss, Precision at a Recall value, AUC PR, and AUC ROC.

To choose the best optimization objective for fraud detection, we need to consider the characteristics of the problem and the data. Fraud detection is a problem where the positive class (fraudulent transactions) is very rare compared to the negative class (legitimate transactions). This means that the data is highly imbalanced, and the model needs to be sensitive to the minority class. Moreover, fraud detection is a problem where the cost of false negatives (missing a fraudulent transaction) is much higher than the cost of false positives (flagging a legitimate transaction as fraudulent). This means that the model needs to have high recall (the ability to detect all fraudulent transactions) while maintaining high precision (the ability to avoid false alarms).

Given these considerations, the best optimization objective for fraud detection is the one that maximizes the area under the precision-recall curve (AUC PR) value. The AUC PR value is a metric that measures the trade-off between precision and recall for different probability thresholds. A higher AUC PR value means that the model can achieve high precision and high recall at the same time. The AUC PR value is also more suitable for imbalanced data than the AUC ROC value, which measures the trade-off between the true positive rate and the false positive rate. The AUC ROC value can be misleading for imbalanced data, as it can give a high score even if the model has low recall or low precision.

Therefore, option C is the correct answer. Option A is not suitable, as Log loss is a metric that measures the difference between the predicted probabilities and the actual labels, and does not account for the trade-off between precision and recall. Option B is not suitable, as Precision at a Recall value is a metric that measures the precision at a fixed recall level, and does not account for the trade-off between precision and recall at different thresholds. Option D is not suitable, as AUC ROC is a metric that can be misleading for imbalanced data, as explained above.

References:

AutoML Tables documentation

Optimization objectives for binary classification

Precision-Recall Curves: How to Easily Evaluate Machine Learning Models in No Time

ROC Curves and Area Under the Curve Explained (video)

 Prediction drift is the change in the distribution of feature values or labels over time. It can affect the performance and accuracy of the model, and may require retraining or redeploying the model. Vertex AI Model Monitoring allows you to monitor prediction drift on your deployed models and endpoints, and set up alerts and notifications when the drift exceeds a certain threshold. You can specify an email address to receive the notifications, and use the information to retrigger the training pipeline and deploy an updated version of your model. This is the most direct and convenient way to achieve your goal. References:

Vertex AI Model Monitoring

Monitoring prediction drift

Setting up alerts and notifications

The best option for creating a scalable and maintainable production process that runs end-to-end and tracks the connections between steps, using prototype code to production, feature engineering code in PySpark that runs on Dataproc Serverless, and model training that is executed by using a Vertex AI custom training job, is to use the Kubeflow pipelines SDK to write code that specifies two components. The first is a Dataproc Serverless component that launches the feature engineering job. The second is a custom component wrapped in the create_custom_training_job_from_component utility that launches the custom model training job. This option allows you to leverage the power and simplicity of Kubeflow pipelines to orchestrate and automate your machine learning workflows on Vertex AI. Kubeflow pipelines is a platform that can build, deploy, and manage machine learning pipelines on Kubernetes. Kubeflow pipelines can help you create reusable and scalable pipelines, experiment with different pipeline versions and parameters, and monitor and debug your pipelines. Kubeflow pipelines SDK is a set of Python packages that can help you build and run Kubeflow pipelines. Kubeflow pipelines SDK can help you define pipeline components, specify pipeline parameters and inputs, and create pipeline steps and tasks. A component is a self-contained set of code that performs one step in a pipeline, such as data preprocessing, model training, or model evaluation. A component can be created from a Python function, a container image, or a prebuilt component. A custom component is a component that is not provided by Kubeflow pipelines, but is created by the user to perform a specific task. A custom component can be wrapped in a utility function that can help you create a Vertex AI custom training job from the component. A custom training job is a resource that can run your custom training code on Vertex AI. A custom training job can help you train various types of models, such as linear regression, logistic regression, k-means clustering, matrix factorization, and deep neural networks. By using the Kubeflow pipelines SDK to write code that specifies two components, the first is a Dataproc Serverless component that launches the feature engineering job, and the second is a custom component wrapped in the create_custom_training_job_from_component utility that launches the custom model training job, you can create a scalable and maintainable production process that runs end-to-end and tracks the connections between steps. You can write code that defines the two components, their inputs and outputs, and their dependencies. You can then use the Kubeflow pipelines SDK to create a pipeline that runs the two components in sequence, and submit the pipeline to Vertex AI Pipelines for execution. By using Dataproc Serverless component, you can run your PySpark feature engineering code on Dataproc Serverless, which is a service that can run Spark batch workloads without provisioning and managing your own cluster. By using custom component wrapped in the create_custom_training_job_from_component utility, you can run your custom model training code on Vertex AI, which is a unified platform for building and deploying machine learning solutions on Google Cloud1.

The other options are not as good as option C, for the following reasons:

Option A: Creating a Vertex AI Workbench notebook, using the notebook to submit the Dataproc Serverless feature engineering job, using the same notebook to submit the custom model training job, and running the notebook cells sequentially to tie the steps together end-to-end would require more skills and steps than using the Kubeflow pipelines SDK to write code that specifies two components, the first is a Dataproc Serverless component that launches the feature engineering job, and the second is a custom component wrapped in the create_custom_training_job_from_component utility that launches the custom model training job. Vertex AI Workbench is a service that can provide managed notebooks for machine learning development and experimentation. Vertex AI Workbench can help you create and run JupyterLab notebooks, and access various tools and frameworks, such as TensorFlow, PyTorch, and JAX. By creating a Vertex AI Workbench notebook, using the notebook to submit the Dataproc Serverless feature engineering job, using the same notebook to submit the custom model training job, and running the notebook cells sequentially to tie the steps together end-to-end, you can create a production process that runs end-to-end and tracks the connections between steps. You can write code that submits the Dataproc Serverless feature engineering job and the custom model training job to Vertex AI, and run the code in the notebook cells. However, creating a Vertex AI Workbench notebook, using the notebook to submit the Dataproc Serverless feature engineering job, using the same notebook to submit the custom model training job, and running the notebook cells sequentially to tie the steps together end-to-end would require more skills and steps than using the Kubeflow pipelines SDK to write code that specifies two components, the first is a Dataproc Serverless component that launches the feature engineering job, and the second is a custom component wrapped in the create_custom_training_job_from_component utility that launches the custom model training job. You would need to write code, create and configure the Vertex AI Workbench notebook, submit the Dataproc Serverless feature engineering job and the custom model training job, and run the notebook cells. Moreover, this option would not use the Kubeflow pipelines SDK, which can simplify the pipeline creation and execution process, and provide various features, such as pipeline parameters, pipeline metrics, and pipeline visualization2.

Option B: Creating a Vertex AI Workbench notebook, initiating an Apache Spark context in the notebook, and running the PySpark feature engineering code, using the same notebook to run the custom model training job in TensorFlow, and running the notebook cells sequentially to tie the steps together end-to-end would not allow you to use Dataproc Serverless to run the feature engineering job, and could increase the complexity and cost of the production process. Apache Spark is a framework that can perform large-scale data processing and machine learning. Apache Spark can help you run various tasks, such as data ingestion, data transformation, data analysis, and data visualization. PySpark is a Python API for Apache Spark. PySpark can help you write and run Spark code in Python. An Apache Spark context is a resource that can initialize and configure the Spark environment. An Apache Spark context can help you create and manage Spark objects, such as SparkSession, SparkConf, and SparkContext. By creating a Vertex AI Workbench notebook, initiating an Apache Spark context in the notebook, and running the PySpark feature engineering code, using the same notebook to run the custom model training job in TensorFlow, and running the notebook cells sequentially to tie the steps together end-to-end, you can create a production process that runs end-to-end and tracks the connections between steps. You can write code that initiates an Apache Spark context and runs the PySpark feature engineering code, and runs the custom model training job in TensorFlow, and run the code in the notebook cells. However, creating a Vertex AI Workbench notebook, initiating an Apache Spark context in the notebook, and running the PySpark feature engineering code, using the same notebook to run the custom model training job in TensorFlow, and running the notebook cells sequentially to tie the steps together end-to-end would not allow you to use Dataproc Serverless to run the feature engineering job, and could increase the complexity and cost of the production process. You would need to write code, create and configure the Vertex AI Workbench notebook, initiate and configure the Apache Spark context, run the PySpark feature engineering code, and run the custom model training job in TensorFlow. Moreover, this option would not use Dataproc Serverless, which is a service that can run Spark batch workloads without provisioning and managing your own cluster, and provide various benefits, such as autoscaling, dynamic resource allocation, and serverless billing2.

Option D: Creating a Vertex AI Pipelines job to link and run both components, using the Kubeflow pipelines SDK to write code that specifies two components, the first component initiates an Apache Spark context that runs the PySpark feature engineering code, and the second component runs the TensorFlow custom model training code, would not allow you to use Dataproc Serverless to run the feature engineering job, and could increase the complexity and cost of the production process. Vertex AI Pipelines is a service that can run Kubeflow pipelines on Vertex AI. Vertex AI Pipelines can help you create and manage machine learning pipelines, and integrate with various Vertex AI services, such as Vertex AI Workbench, Vertex AI Training, and Vertex AI Prediction. A Vertex AI Pipelines job is a resource that can execute a pipeline on Vertex AI Pipelines. A Vertex AI Pipelines job can help you run your pipeline steps and tasks, and monitor and debug your pipeline execution. By creating a Vertex AI Pipelines job to link and run both components, using the Kubeflow pipelines SDK to write code that specifies two components, the first component initiates an Apache Spark context that runs the PySpark feature engineering code, and the second component runs the TensorFlow custom model training code, you can create a scalable and maintainable production process that runs end-to-end and tracks the connections between steps. You can write code that defines the two components, their inputs and outputs, and their dependencies. You can then use the Kubeflow pipelines SDK to create a pipeline that runs the two components in sequence, and submit the pipeline to Vertex AI Pipelines for execution. However, creating a Vertex AI Pipelines job to link and run both components, using the Kubeflow pipelines SDK to write code that specifies two components, the first component initiates an Apache Spark context that runs the PySpark feature engineering code,

The best option for implementing the processing steps so that they run at serving time, minimizing code changes and infrastructure maintenance, and deploying the model into production as quickly as possible, is to use the Predictor interface to implement a custom prediction routine. Build the custom container, upload the container to Vertex AI Model Registry, and deploy it to a Vertex AI endpoint. This option allows you to leverage the power and simplicity of Vertex AI to serve your XGBoost model with minimal effort and customization. Vertex AI is a unified platform for building and deploying machine learning solutions on Google Cloud. Vertex AI can deploy a trained XGBoost model to an online prediction endpoint, which can provide low-latency predictions for individual instances. A custom prediction routine (CPR) is a Python script that defines the logic for preprocessing the input data, running the prediction, and postprocessing the output data. A CPR can help you customize the prediction behavior of your model, and handle complex or non-standard data formats. A CPR can also help you minimize the code changes, as you only need to write a few functions to implement the prediction logic. A Predictor interface is a class that inherits from the base class aiplatform.Predictor, and implements the abstract methods predict() and preprocess(). A Predictor interface can help you create a CPR by defining the preprocessing and prediction logic for your model. A container image is a package that contains the model, the CPR, and the dependencies. A container image can help you standardize and simplify the deployment process, as you only need to upload the container image to Vertex AI Model Registry, and deploy it to Vertex AI Endpoints. By using the Predictor interface to implement a CPR, building the custom container, uploading the container to Vertex AI Model Registry, and deploying it to a Vertex AI endpoint, you can implement the processing steps so that they run at serving time, minimize code changes and infrastructure maintenance, and deploy the model into production as quickly as possible1.

The other options are not as good as option C, for the following reasons:

Option A: Using FastAPI to implement an HTTP server, creating a Docker image that runs your HTTP server, and deploying it on your organization’s GKE cluster would require more skills and steps than using the Predictor interface to implement a CPR, building the custom container, uploading the container to Vertex AI Model Registry, and deploying it to a Vertex AI endpoint. FastAPI is a framework for building web applications and APIs in Python. FastAPI can help you implement an HTTP server that can handle prediction requests and responses, and perform data preprocessing and postprocessing. A Docker image is a package that contains the model, the HTTP server, and the dependencies. A Docker image can help you standardize and simplify the deployment process, as you only need to build and run the Docker image. GKE is a service that can create and manage Kubernetes clusters on Google Cloud. GKE can help you deploy and scale your Docker image on Google Cloud, and provide high availability and performance. However, using FastAPI to implement an HTTP server, creating a Docker image that runs your HTTP server, and deploying it on your organization’s GKE cluster would require more skills and steps than using the Predictor interface to implement a CPR, building the custom container, uploading the container to Vertex AI Model Registry, and deploying it to a Vertex AI endpoint. You would need to write code, create and configure the HTTP server, build and test the Docker image, create and manage the GKE cluster, and deploy and monitor the Docker image. Moreover, this option would not leverage the power and simplicity of Vertex AI, which can provide online prediction natively integrated with Google Cloud services2.

Option B: Using FastAPI to implement an HTTP server, creating a Docker image that runs your HTTP server, uploading the image to Vertex AI Model Registry, and deploying it to a Vertex AI endpoint would require more skills and steps than using the Predictor interface to implement a CPR, building the custom container, uploading the container to Vertex AI Model Registry, and deploying it to a Vertex AI endpoint. FastAPI is a framework for building web applications and APIs in Python. FastAPI can help you implement an HTTP server that can handle prediction requests and responses, and perform data preprocessing and postprocessing. A Docker image is a package that contains the model, the HTTP server, and the dependencies. A Docker image can help you standardize and simplify the deployment process, as you only need to build and run the Docker image. Vertex AI Model Registry is a service that can store and manage your machine learning models on Google Cloud. Vertex AI Model Registry can help you upload and organize your Docker image, and track the model versions and metadata. Vertex AI Endpoints is a service that can provide online prediction for your machine learning models on Google Cloud. Vertex AI Endpoints can help you deploy your Docker image to an online prediction endpoint, which can provide low-latency predictions for individual instances. However, using FastAPI to implement an HTTP server, creating a Docker image that runs your HTTP server, uploading the image to Vertex AI Model Registry, and deploying it to a Vertex AI endpoint would require more skills and steps than using the Predictor interface to implement a CPR, building the custom container, uploading the container to Vertex AI Model Registry, and deploying it to a Vertex AI endpoint. You would need to write code, create and configure the HTTP server, build and test the Docker image, upload the Docker image to Vertex AI Model Registry, and deploy the Docker image to Vertex AI Endpoints. Moreover, this option would not leverage the power and simplicity of Vertex AI, which can provide online prediction natively integrated with Google Cloud services2.

Option D: Using the XGBoost prebuilt serving container when importing the trained model into Vertex AI, deploying the model to a Vertex AI endpoint, working with the backend engineers to implement the pre- and postprocessing steps in the Golang backend service would not allow you to implement the processing steps so that they run at serving time, and could increase the code changes and infrastructure maintenance. A XGBoost prebuilt serving container is a container image that is provided by Google Cloud, and contains the XGBoost framework and the dependencies. A XGBoost prebuilt serving container can help you deploy a XGBoost model without writing any code, but it also limits your customization options. A XGBoost prebuilt serving container can only handle standard data formats, such as JSON or CSV, and cannot perform any preprocessing or postprocessing on the input or output data. If your input data requires any transformation or normalization before running the prediction, you cannot use a XGBoost prebuilt serving container. A Golang backend service is a service that is implemented in Golang, a programming language that can be used for web development and system programming. A Golang backend service can help you handle the prediction requests and responses from the frontend, and communicate with the Vertex AI endpoint. However, using the XGBoost prebuilt serving container when importing the trained model into Vertex AI, deploying the model to a Vertex AI endpoint, working with the backend engineers to implement the pre- and postprocessing steps in the Golang backend service would not allow you to implement the processing steps so that they run at serving time, and could increase the code changes and infrastructure maintenance. You would need to write code, import the trained model into Vertex AI, deploy the model to a Vertex AI endpoint, implement the pre- and postprocessing steps in the Golang backend service, and test and monitor the Golang backend service. Moreover, this option would not leverage the power and simplicity of Vertex AI, which can provide online prediction natively integrated with Google Cloud services2.

References:

Preparing for Google Cloud Certification: Machine Learning Engineer, Course 3: Production ML Systems, Week 2: Serving ML Predictions

Google Cloud Professional Machine Learning Engineer Exam Guide, Section 3: Scaling ML models in production, 3.1 Deploying ML models to production

Official Google Cloud Certified Professional Machine Learning Engineer Study Guide, Chapter 6: Production ML Systems, Section 6.2: Serving ML Predictions

Custom prediction routines

Using pre-built containers for prediction

Using custom containers for prediction

Vertex AI is a unified platform for building and deploying ML models on Google Cloud. It supports both custom and AutoML models, and provides various tools and services for ML development, such as Vertex Pipelines, Vertex Vizier, Vertex Explainable AI, and Vertex Feature Store. Vertex AI can be used to create models for predicting ticket priority and resolution time, as these are domain-specific tasks that require custom training data and evaluation metrics. Cloud Natural Language API is a pre-trained service that provides natural language understanding capabilities, such as sentiment analysis, entity analysis, syntax analysis, and content classification. Cloud Natural Language API can be used to perform sentiment analysis on the support tickets, as this is a general task that does not require domain-specific knowledge or jargon. The other options are not suitable for the given architecture. AutoML Natural Language and AutoML Vision are services that allow users to create custom natural language and vision models using their own data and labels. They are not needed for sentiment analysis, as Cloud Natural Language API already provides this functionality. Cloud Vision API is a pre-trained service that provides image analysis capabilities, such as object detection, face detection, text detection, and image labeling. It is not relevant for the support tickets, as they are not expected to have any images. References:

Vertex AI documentation

Cloud Natural Language API documentation

 Before building an insurance approval model, an ML engineer should consider the factors of traceability, reproducibility, and explainability, as these are important aspects of responsible AI and fairness in a regulated domain. Traceability is the ability to track the provenance and lineage of the data, models, and decisions throughout the ML lifecycle. It helps to ensure the quality, reliability, and accountability of the ML system, and to comply with the regulatory and ethical standards. Reproducibility is the ability to recreate the same results and outcomes using the same data, models, and parameters. It helps to verify the validity, consistency, and robustness of the ML system, and to debug and improve the performance. Explainability is the ability to understand and interpret the logic, behavior, and outcomes of the ML system. It helps to increase the transparency, trust, and confidence of the ML system, and to identify and mitigate any potential biases, errors, or risks. The other options are not as relevant or comprehensive as this option. Redaction is the process of removing sensitive or confidential information from the data or documents, but it is not a factor that the ML engineer should consider before building the model, as it is more related to the data preparation and protection. Federated learning is a technique that allows training ML models on decentralized data without transferring the data to a central server, but it is not a factor that the ML engineer should consider before building the model, as it is more related to the model architecture and privacy preservation. Differential privacy is a method that adds noise to the data or the model outputs to protect the individual privacy of the data subjects, but it is not a factor that the ML engineer should consider before building the model, as it is more related to the model evaluation and deployment. References:

Responsible AI documentation

Traceability documentation

Reproducibility documentation

Explainability documentation

 AutoML Natural Language is a service that allows users to create custom natural language models using their own data and labels. It supports various natural language tasks, such as text classification, entity extraction, and sentiment analysis. AutoML Natural Language can be used to build a model to classify incoming calls by product, as it can extract custom entities from the transcribed calls and assign them to predefined categories. AutoML Natural Language also minimizes data preprocessing and development time, as it handles the data preparation, model training, and evaluation automatically. The other options are not as suitable for this scenario. AI Platform Training built-in algorithms are a set of pre-defined algorithms that can be used to train ML models on AI Platform, but they do not support natural language processing tasks. Cloud Natural Language API is a pre-trained service that provides natural language understanding capabilities, such as sentiment analysis, entity analysis, syntax analysis, and content classification. However, it does not support custom entities or categories, and may not recognize the product names from the calls. Building a custom model to identify the product keywords and then running them through a classification algorithm would require more data preprocessing and development time, as well as more coding and testing. References:

AutoML Natural Language documentation

AI Platform Training built-in algorithms documentation

Cloud Natural Language API documentation

The best approach to build a model that predicts how much inventory the logistics team should order each month is to use a time series forecasting model to predict each item’s monthly sales. This approach can capture the temporal patterns and trends in the sales data, such as seasonality, cyclicality, and autocorrelation. It can also account for the variability and uncertainty in the demand, and provide confidence intervals and error metrics for the predictions. By using a time series forecasting model, you can provide the logistics team with accurate and reliable estimates of the future sales for each item, which can help them optimize the inventory levels and avoid overstocking or understocking. You can use various methods and tools to build a time series forecasting model, such as ARIMA, LSTM, Prophet, or BigQuery ML.

The other options are not optimal for the following reasons:

A. Using a clustering algorithm to group popular items together is not a good approach, as it does not provide any quantitative or temporal information about the sales or the inventory. It only provides a qualitative and static categorization of the items based on their similarity or dissimilarity. Moreover, clustering is an unsupervised learning technique, which does not use any target variable or feedback to guide the learning process. This can result in arbitrary and inconsistent clusters, which may not reflect the true demand or preferences of the customers.

B. Using a regression model to predict how much additional inventory should be purchased each month is not a good approach, as it does not account for the individual differences and dynamics of each item. It only provides a single aggregated value for the whole inventory, which can be misleading and inaccurate. Moreover, a regression model is not well-suited for handling time series data, as it assumes that the data points are independent and identically distributed, which is not the case for sales data. A regression model can also suffer from overfitting or underfitting, depending on the choice and complexity of the features and the model.

D. Using a classification model to classify inventory levels as UNDER_STOCKED, OVER_STOCKED, and CORRECTLY_STOCKED is not a good approach, as it does not provide any numerical or predictive information about the sales or the inventory. It only provides a discrete and subjective label for the inventory levels, which can be vague and ambiguous. Moreover, a classification model is not well-suited for handling time series data, as it assumes that the data points are independent and identically distributed, which is not the case for sales data. A classification model can also suffer from class imbalance, misclassification, or overfitting, depending on the choice and complexity of the features, the model, and the threshold.

References:

Professional ML Engineer Exam Guide

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Google Cloud launches machine learning engineer certification

Time Series Forecasting: Principles and Practice

BigQuery ML: Time series analysis

 AutoML Vision is a Google Cloud service that allows you to train custom ML models for image classification, object detection, and segmentation without writing any code. You can use AutoML Vision to upload your training data, label it, and train a model using a graphical user interface. You can also evaluate the model’s performance and export it for deployment. One of the export options is Core ML, which is a framework that lets you integrate ML models into iOS applications. Core ML optimizes the model for on-device performance, power efficiency, and minimal memory footprint. By using AutoML Vision and Core ML, you can minimize code development and have a model that is optimized for inference on mobile phones. References:

AutoML Vision documentation

Core ML documentation

The best hardware to choose for your model while minimizing cost is a Vertex AI Workbench user-managed notebooks instance running on an n1-standard-16 with a preemptible v3-8 TPU. This hardware configuration can provide you with high performance, scalability, and efficiency for your TensorFlow model, as well as low cost and flexibility for your long-running and checkpointing process. The v3-8 TPU is a cloud tensor processing unit (TPU) device, which is a custom ASIC chip designed by Google to accelerate ML workloads. It can handle large and complex models and datasets, and offer fast and stable training and inference. The n1-standard-16 is a general-purpose VM that can support the CPU and memory requirements of your model, as well as the data preprocessing and postprocessing tasks. By choosing a preemptible v3-8 TPU, you can take advantage of the lower price and availability of the TPU devices, as long as you can tolerate the possibility of the device being reclaimed by Google at any time. However, since you have built frequent checkpointing into your training process, you can resume your model from the last saved state, and avoid losing any progress or data. Moreover, you can use the Vertex AI Workbench user-managed notebooks to create and manage your notebooks instances, and leverage the integration with Vertex AI and other Google Cloud services.

The other options are not optimal for the following reasons:

A. A Vertex AI Workbench user-managed notebooks instance running on an n1-standard-16 with 4 NVIDIA P100 GPUs is not a good option, as it has higher cost and lower performance than the v3-8 TPU. The NVIDIA P100 GPUs are the previous generation of GPUs from NVIDIA, which have lower performance, scalability, and efficiency than the latest NVIDIA A100 GPUs or the TPUs. They also have higher price and lower availability than the preemptible TPUs, which can increase the cost and complexity of your solution.

B. A Vertex AI Workbench user-managed notebooks instance running on an n1-standard-16 with an NVIDIA P100 GPU is not a good option, as it has higher cost and lower performance than the v3-8 TPU. It also has less GPU memory and compute power than the option with 4 NVIDIA P100 GPUs, which can limit the size and complexity of your model, and affect the training and inference speed and quality.

C. A Vertex AI Workbench user-managed notebooks instance running on an n1-standard-16 with a non-preemptible v3-8 TPU is not a good option, as it has higher cost and lower flexibility than the preemptible v3-8 TPU. The non-preemptible v3-8 TPU has the same performance, scalability, and efficiency as the preemptible v3-8 TPU, but it has higher price and lower availability, as it is reserved for your exclusive use. Moreover, since your model is long-running and checkpointing, you do not need the guarantee of the device not being reclaimed by Google, and you can benefit from the lower cost and higher availability of the preemptible v3-8 TPU.

References:

Professional ML Engineer Exam Guide

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Google Cloud launches machine learning engineer certification

Cloud TPU

Vertex AI Workbench user-managed notebooks

Preemptible VMs

NVIDIA Tesla P100 GPU

According to the web search results, BigQuery ML1 is a service that allows you to create and execute machine learning models in BigQuery using SQL queries. BigQuery ML supports various types of models, such as linear regression, logistic regression, k-means clustering, matrix factorization, deep neural networks, and time series forecasting1. ARIMA_PLUS2 is a statistical model for time series forecasting that is built in to BigQuery ML. ARIMA_PLUS stands for AutoRegressive Integrated Moving Average with eXogenous regressors. ARIMA_PLUS models the relationship between a target variable and its past values, as well as other external factors that might influence the target variable. ARIMA_PLUS can handle multiple time series, seasonality, holidays, and missing values2. Therefore, option C is the best way to use a solution that can be implemented quickly with minimal effort for the given use case, as it allows you to use SQL queries to build and run a forecasting model in BigQuery without moving the data or writing custom code. The other options are not relevant or optimal for this scenario. References:

BigQuery ML

ARIMA_PLUS

Google Professional Machine Learning Certification Exam 2023

Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

Vertex AI Model Registry supports traffic splitting and built-in monitoring, making A/B testing seamless. This approach eliminates the need for additional monitoring tools and infrastructure overhead. Cloud Run and GKE solutions (Options A and C) add unnecessary complexity, while Looker Studio (Option B) requires additional configuration for monitoring.

=================

Vertex AI Feature Store provides two options for online serving: Bigtable and optimized online serving. Both options support autoscaling, which means that the number of online serving nodes can automatically adjust to the traffic demand. By enabling autoscaling, you can improve the online serving performance and reduce the feature retrieval latency during the daily batch ingestion. Autoscaling also helps you optimize the cost and resource utilization of your featurestore. References:

Online serving | Vertex AI | Google Cloud

New Vertex AI Feature Store: BigQuery-Powered, GenAI-Ready | Google Cloud Blog

Cloud Vision API offers pre-trained models specialized in identifying explicit or inappropriate content. By sending a copy of each image to a Cloud Storage bucket and triggering Cloud Vision through Cloud Run, the detection of explicit content is automated with minimal development time. Vertex AI custom models require more training data and infrastructure management, while AutoML-based solutions add more complexity. Cloud Vision’s existing capabilities meet the requirement effectively and are highly scalable for real-time moderation needs.

=================

The best option for creating a Dataflow pipeline for real-time anomaly detection is to load the model directly into the Dataflow job as a dependency, and use it for prediction. This option has the following advantages:

It minimizes the serving latency, as the model prediction logic is executed within the same Dataflow pipeline that ingests and processes the data. There is no need to invoke external services or containers, which can introduce network overhead and latency.

It simplifies the deployment and management of the model, as the model is packaged with the Dataflow job and does not require a separate service or container. The model can be updated by redeploying the Dataflow job with a new model version.

It leverages the scalability and reliability of Dataflow, as the model prediction logic can scale up or down with the data volume and handle failures and retries automatically.

The other options are less optimal for the following reasons:

Option A: Containerizing the model prediction logic in Cloud Run, which is invoked by Dataflow, introduces additional latency and complexity. Cloud Run is a serverless platform that runs stateless containers, which means that the model prediction logic needs to be initialized and loaded every time a request is made. This can increase the cold start latency and reduce the throughput. Moreover, Cloud Run has a limit on the number of concurrent requests per container, which can affect the scalability of the model prediction logic. Additionally, this option requires managing two separate services: the Dataflow pipeline and the Cloud Run container.

Option C: Deploying the model to a Vertex AI endpoint, and invoking this endpoint in the Dataflow job, also introduces additional latency and complexity. Vertex AI is a managed service that provides various tools and features for machine learning, such as training, tuning, serving, and monitoring. However, invoking a Vertex AI endpoint from a Dataflow job requires making an HTTP request, which can incur network overhead and latency. Moreover, this option requires managing two separate services: the Dataflow pipeline and the Vertex AI endpoint.

Option D: Deploying the model in a TFServing container on Google Kubernetes Engine, and invoking it in the Dataflow job, also introduces additional latency and complexity. TFServing is a high-performance serving system for TensorFlow models, which can handle multiple versions and variants of a model. However, invoking a TFServing container from a Dataflow job requires making a gRPC or REST request, which can incur network overhead and latency. Moreover, this option requires managing two separate services: the Dataflow pipeline and the Google Kubernetes Engine cluster.

References:

[Dataflow documentation]

[TensorFlow documentation]

[Cloud Run documentation]

[Vertex AI documentation]

[TFServing documentation]

Precision measures the fraction of messages flagged by the model that are actually inappropriate, while recall measures the fraction of inappropriate messages that are flagged by the model. These metrics are useful for evaluating how well the model can identify and filter out inappropriate comments.

Option A is not a good metric because it does not account for the accuracy of the model. The model might flag many messages that are not inappropriate, or miss many messages that are inappropriate.

Option B is better than option A, but it still does not account for the recall of the model. The model might flag only a few messages that are highly likely to be inappropriate, but miss many other messages that are less obvious but still inappropriate.

Option C is not a good metric because it does not focus on the messages that are flagged by the model. The random sample of 0.1% of raw messages might contain very few inappropriate messages, making the precision and recall estimates unreliable.

The F1 score is a metric that combines both precision and recall, and is suitable for evaluating imbalanced classification problems. Precision measures the fraction of true positives among the predicted positives, and recall measures the fraction of true positives among the actual positives. The F1 score is the harmonic mean of precision and recall, and it ranges from 0 to 1, with higher values indicating better performance. The F1 score is a good metric for imbalanced data because it balances both the false positives and the false negatives, and does not favor the majority class over the minority class.

The other options are not good metrics for imbalanced data. RMSE (root mean squared error) is a metric for regression problems, not classification problems. It measures the average squared difference between the predicted and the actual values, and is not suitable for binary outcomes. F score with higher precision weighting than recall, or F0.5 score, is a metric that gives more importance to precision than recall. This means that it penalizes false positives more than false negatives, which is not desirable for imbalanced data where the minority class is more important. F score with higher recall weighting than precision, or F2 score, is a metric that gives more importance to recall than precision. This means that it penalizes false negatives more than false positives, which might be suitable for some imbalanced data problems, but not for the logo detection problem. In this problem, both false positives and false negatives are equally important, as we want to accurately identify the presence or absence of a logo in an image. Therefore, the F1 score is a better metric than the F2 score. References:

Tour of Evaluation Metrics for Imbalanced Classification

Metrics for imbalanced data (simply explained)

Medical entity extraction is a task that involves identifying and classifying medical terms or concepts from unstructured textual data, such as electronic health records, clinical notes, or research papers. Medical entity extraction can help with various use cases, such as information retrieval, knowledge discovery, decision support, and data analysis1.

One possible approach to perform medical entity extraction is to use a BERT-based model to fine-tune a medical entity extraction model. BERT (Bidirectional Encoder Representations from Transformers) is a pre-trained language model that can capture the contextual information from both left and right sides of a given token2. BERT can be fine-tuned on a specific downstream task, such as medical entity extraction, by adding a task-specific layer on top of the pre-trained model and updating the model parameters with a small amount of labeled data3.

A BERT-based model can achieve high performance on medical entity extraction by leveraging the large-scale pre-training on general-domain corpora and the fine-tuning on domain-specific data. For example, Nesterov and Umerenkov4 proposed a novel method of doing medical entity extraction from electronic health records as a single-step multi-label classification task by fine-tuning a transformer model pre-trained on a large EHR dataset. They showed that their model can achieve human-level quality for most frequent entities.

References:

1: Medical Named Entity Recognition from Un-labelled Medical Records based on Pre-trained Language Models and Domain Dictionary | Data Intelligence | MIT Press

2: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

3: Fine-tuning BERT for Medical Entity Extraction

4: Distantly supervised end-to-end medical entity extraction from electronic health records with human-level quality

 Labels are key-value pairs that can be attached to any AI Platform resource, such as jobs, models, versions, or endpoints1. Labels can help you organize your resources into descriptive categories, such as project, team, environment, or purpose. You can use labels to filter the results when you list or monitor your resources, or to group them for billing or quota purposes2. Using labels is a simple and scalable way to manage your AI Platform resources without creating unnecessary complexity or overhead. Therefore, using labels to organize resources is the best strategy for this use case.

References:

Using labels

Filtering and grouping by labels

 Labels are key-value pairs that you can attach to AI Platform resources such as jobs, models, and versions. Labels can help you organize your resources into descriptive categories that reflect your business needs. For example, you can use labels to indicate the owner, purpose, environment, or status of a resource. You can also use labels to filter the results when you list or monitor your resources on the Google Cloud Console or the Cloud SDK. Using labels can help you manage your resources in a clean and scalable way, without requiring separate projects or restrictive permissions.

References:

Using labels to organize AI Platform resources

Creating and managing labels

QUESTION 52

You are training a deep learning model for semantic image segmentation with reduced training time. While using a Deep Learning VM Image, you receive the following error: The resource 'projects/deeplearning-platforn/zones/europe-west4-c/acceleratorTypes/nvidia-tesla-k80' was not found. What should you do?

A. Ensure that you have GPU quota in the selected region.

B. Ensure that the required GPU is available in the selected region.

C. Ensure that you have preemptible GPU quota in the selected region.

D. Ensure that the selected GPU has enough GPU memory for the workload.

Answer: B

The error message indicates that the selected GPU type (nvidia-tesla-k80) is not available in the selected region (europe-west4-c). This can happen when the GPU type is not supported in the region, or when the GPU quota is exhausted in the region. To avoid this error, you should ensure that the required GPU is available in the selected region before creating a Deep Learning VM Image. You can use the following steps to check the GPU availability and quota:

To check the GPU availability, you can use the gcloud compute accelerator-types list command with the --filter flag to specify the GPU type and the region. For example, to check the availability of nvidia-tesla-k80 in europe-west4-c, you can run:

gcloud compute accelerator-types list --filter="name=nvidia-tesla-k80 AND zone:europe-west4-c"

If the command returns an empty result, it means that the GPU type is not supported in the region. You can either choose a different GPU type or a different region that supports the GPU type. You can use the same command without the --filter flag to list all the available GPU types and regions. For example, to list all the available GPU types in europe-west4-c, you can run:

gcloud compute accelerator-types list --filter="zone:europe-west4-c"

To check the GPU quota, you can use the gcloud compute regions describe command with the --format flag to specify the region and the quota metric. For example, to check the quota for nvidia-tesla-k80 in europe-west4-c, you can run:

gcloud compute regions describe europe-west4-c --format="value(quotas.NVIDIA_K80_GPUS)"

If the command returns a value of 0, it means that the GPU quota is exhausted in the region. You can either request more quota from Google Cloud or choose a different region that has enough quota for the GPU type.

References:

Troubleshooting | Deep Learning VM Images | Google Cloud

Checking GPU availability

Checking GPU quota

 Comparing the training and evaluation losses of the current run is a good way to check if the model is overfitting or underfitting. If the losses are similar, it means that the model is generalizing well and can be deployed to a Vertex AI endpoint. Vertex AI endpoint is a service that allows you to serve your ML models online and scale them automatically. By using a training/serving skew threshold model monitoring, you can detect if there is a significant difference between the data used for training and the data used for serving. This can indicate that the model is becoming stale or inaccurate over time. When the model monitoring threshold is triggered, it means that the model needs to be retrained with the latest data. By redeploying the pipeline, you can automate the retraining process and update the model with the new data. This way, you can minimize the cost of retraining and ensure that your model is always up-to-date and accurate. References:

Vertex AI documentation

Vertex AI endpoint documentation

Model monitoring documentation

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

The best option to minimize storage and computational overhead is to use the TRANSFORM clause in the CREATE MODEL statement in the SQL query to calculate the required statistics. The TRANSFORM clause allows you to specify feature preprocessing logic that applies to both training and prediction. The preprocessing logic is executed in the same query as the model creation, which avoids the need to create and store intermediate tables. The TRANSFORM clause also supports quantile bucketization and MinMax scaling, which are the preprocessing steps required for this scenario. Option A is incorrect because creating a component in the Vertex AI Pipelines DAG to calculate the required statistics may increase the computational overhead, as the component needs to run separately from the model creation. Moreover, the component needs to pass the statistics to subsequent components, which may increase the storage overhead. Option B is incorrect because preprocessing and staging the data in BigQuery prior to feeding it to the model may also increase the storage and computational overhead, as you need to create and maintain additional tables for the preprocessed data. Moreover, you need to ensure that the preprocessing logic is consistent for both training and inference. Option C is incorrect because creating SQL queries to calculate and store the required statistics in separate BigQuery tables may also increase the storage and computational overhead, as you need to create and maintain additional tables for the statistics. Moreover, you need to ensure that the statistics are updated regularly to reflect the new data. References:

BigQuery ML documentation

Using the TRANSFORM clause

Feature preprocessing with BigQuery ML

Vertex AI is a unified platform for building and managing machine learning solutions on Google Cloud. It provides a managed service for training custom models with various frameworks, such as TensorFlow, PyTorch, scikit-learn, and XGBoost. To train your PyTorch model with Vertex AI, you need to package your code with Setuptools, which is a Python tool for creating and distributing packages. You also need to use a pre-built container, which is a Docker image that contains the dependencies and libraries for your framework. You can choose from a list of pre-built containers provided by Google, or create your own custom container. By using a pre-built container, you can avoid the hassle of installing and configuring the environment for your model. You can also specify a custom tier for your training job, which allows you to select the number and type of GPUs you want to use. You can choose from various GPU options, such as V100, P100, K80, and T4. By using 4 V100 GPUs, you can leverage the high performance and memory capacity of these accelerators to train your model faster and cheaper than using CPUs. This solution requires minimal changes to your code and can scale your training workload efficiently. References:

Vertex AI | Google Cloud

Custom training with pre-built containers | Vertex AI

[Using GPUs | Vertex AI]

According to the official exam guide1, one of the skills assessed in the exam is to “design, build, and productionalize ML models to solve business challenges using Google Cloud technologies”. Dataflow2 is a fully managed, fast, and easy-to-use service for running Apache Spark and Apache Hadoop clusters on Google Cloud. Dataflow supports both batch and streaming data processing pipelines. However, if your use case requires real-time inference, you need to ensure that the data preprocessing logic is applied consistently between training and serving. One way to achieve this is to refactor the transformation code in the batch data pipeline so that it can be used outside of the pipeline, and use the same code in the endpoint. This way, you can avoid data skew and drift issues that might arise from using different preprocessing methods for training and serving. Therefore, option B is the best way to ensure the data preprocessing logic is applied consistently between training and serving. The other options are not relevant or optimal for this scenario. References:

Professional ML Engineer Exam Guide

Dataflow

Google Professional Machine Learning Certification Exam 2023

Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

Vertex AI Pipelines is a service that allows you to create and run scalable and portable ML pipelines on Google Cloud. You can use Vertex AI Pipelines to add a component to divide the data into training and evaluation sets, and add another component for feature engineering. A component is a self-contained piece of code that performs a specific task in the pipeline. You can use the built-in components provided by Vertex AI Pipelines, or create your own custom components. By using Vertex AI Pipelines, you can orchestrate and automate your ML workflow, and track the provenance and lineage of your data and models. You can also enable autologging of metrics in the training component, which is a feature that automatically logs the metrics from your XGBoost model to Vertex AI Experiments. Vertex AI Experiments is a service that allows you to track, compare, and optimize your ML experiments on Google Cloud. You can use Vertex AI Experiments to monitor the training progress, visualize the metrics, and analyze the results of your model. You can also compare models using the artifacts lineage in Vertex ML Metadata. Vertex ML Metadata is a service that stores and manages the metadata of your ML artifacts, such as datasets, models, metrics, and executions. You can use Vertex ML Metadata to view the artifacts lineage, which is a graph that shows the relationships and dependencies among the artifacts. By using the artifacts lineage, you can compare the performance and quality of different models trained in different pipeline executions, and identify the best model for your use case. By using Vertex AI Pipelines, Vertex AI Experiments, and Vertex ML Metadata, you can execute the steps required for developing a training pipeline for a new XGBoost classification model based on tabular data stored in a BigQuery table. References:

Vertex AI Pipelines documentation

Vertex AI Experiments documentation

Vertex ML Metadata documentation

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

 A cloud-based backend system is a system that runs on a cloud platform and provides services or resources to other applications or users. A cloud-based backend system can be used to submit training jobs, which are tasks that involve training a machine learning model on a given dataset using a specific framework and configuration1

However, a cloud-based backend system can also have some drawbacks, such as:

High maintenance: A cloud-based backend system may require a lot of administration and management, such as provisioning, scaling, monitoring, and troubleshooting the cloud resources and services. This can be time-consuming and costly, and may distract from the core business objectives2

Low flexibility: A cloud-based backend system may not support all the frameworks and libraries that the data scientists need to use for their training jobs. This can limit the choices and capabilities of the data scientists, and affect the quality and performance of their models3

Poor integration: A cloud-based backend system may not integrate well with other cloud services or tools that the data scientists need to use for their machine learning workflows, such as data processing, model deployment, or model monitoring. This can create compatibility and interoperability issues, and reduce the efficiency and productivity of the data scientists.

Therefore, it may be better to use a managed service instead of a cloud-based backend system to submit training jobs. A managed service is a service that is provided and operated by a third-party provider, and offers various benefits, such as:

Low maintenance: A managed service handles the administration and management of the cloud resources and services, and abstracts away the complexity and details of the underlying infrastructure. This can save time and money, and allow the data scientists to focus on their core tasks2

High flexibility: A managed service can support multiple frameworks and libraries that the data scientists need to use for their training jobs, and allow them to customize and configure their training environments and parameters. This can enhance the choices and capabilities of the data scientists, and improve the quality and performance of their models3

Easy integration: A managed service can integrate seamlessly with other cloud services or tools that the data scientists need to use for their machine learning workflows, and provide a unified and consistent interface and experience. This can solve the compatibility and interoperability issues, and increase the efficiency and productivity of the data scientists.

One of the best options for using a managed service to submit training jobs is to use the AI Platform custom containers feature to receive training jobs using any framework. AI Platform is a Google Cloud service that provides a platform for building, deploying, and managing machine learning models. AI Platform supports various machine learning frameworks, such as TensorFlow, PyTorch, scikit-learn, and XGBoost, and provides various features, such as hyperparameter tuning, distributed training, online prediction, and model monitoring.

The AI Platform custom containers feature allows the data scientists to use any framework or library that they want for their training jobs, and package their training application and dependencies as a Docker container image. The data scientists can then submit their training jobs to AI Platform, and specify the container image and the training parameters. AI Platform will run the training jobs on the cloud infrastructure, and handle the scaling, logging, and monitoring of the training jobs. The data scientists can also use the AI Platform features to optimize, deploy, and manage their models.

The other options are not as suitable or feasible. Configuring Kubeflow to run on Google Kubernetes Engine and receive training jobs through TFJob is not ideal, as Kubeflow is mainly designed for TensorFlow-based training jobs, and does not support other frameworks or libraries. Creating a library of VM images on Compute Engine and publishing these images on a centralized repository is not optimal, as Compute Engine is a low-level service that requires a lot of administration and management, and does not provide the features and integrations of AI Platform. Setting up Slurm workload manager to receive jobs that can be scheduled to run on your cloud infrastructure is not relevant, as Slurm is a tool for managing and scheduling jobs on a cluster of nodes, and does not provide a managed service for training jobs.

References: 1: Cloud computing 2: Managed services 3: Machine learning frameworks : [Machine learning workflow] : [AI Platform overview] : [Custom containers for training]

AI Platform Training is a service that allows you to run your machine learning experiments on Google Cloud using various features, model architectures, and hyperparameters. You can use AI Platform Training to scale up your experiments, leverage distributed training, and access specialized hardware such as GPUs and TPUs1. Cloud Monitoring is a service that collects and analyzes metrics, logs, and traces from Google Cloud, AWS, and other sources. You can use Cloud Monitoring to create dashboards, alerts, and reports based on your data2. The Monitoring API is an interface that allows you to programmatically access and manipulate your monitoring data3.

By using AI Platform Training and Cloud Monitoring, you can track and report your experiments while minimizing manual effort. You can write the accuracy metrics from your experiments to Cloud Monitoring using the AI Platform Training Python package4. You can then query the results using the Monitoring API and compare the performance of different experiments. You can also visualize the metrics in the Cloud Console or create custom dashboards and alerts5. Therefore, using AI Platform Training and Cloud Monitoring is the best option for this use case.

References:

AI Platform Training documentation

Cloud Monitoring documentation

Monitoring API overview

Using Cloud Monitoring with AI Platform Training

Viewing evaluation metrics

 The best options for adjusting the training parameters in AutoML to improve model performance are to decrease the score threshold and add more positive examples to the training set. These options can help increase the detection rate of fraudulent transactions, which is the priority for this use case. The score threshold is a parameter that determines the minimum probability score that a prediction must have to be classified as positive. Decreasing the score threshold can increase the recall of the model, which is the proportion of actual positive cases that are correctly identified. Increasing the recall can help reduce the number of false negatives, which are fraudulent transactions that are missed by the model. However, decreasing the score threshold can also decrease the precision of the model, which is the proportion of positive predictions that are actually correct. Decreasing the precision can increase the number of false positives, which are legitimate transactions that are flagged as fraudulent by the model. Therefore, there is a trade-off between recall and precision, and the optimal score threshold depends on the business objective and the cost of errors1. Adding more positive examples to the training set can help balance the data distribution and improve the model performance. Positive examples are the instances that belong to the target class, which in this case are fraudulent transactions. Negative examples are the instances that belong to the other class, which in this case are legitimate transactions. Fraudulent transactions are usually rare and imbalanced compared to legitimate transactions, which can cause the model to be biased towards the majority class and fail to learn the characteristics of the minority class. Adding more positive examples can help the model learn more features and patterns of the fraudulent transactions, and increase the detection rate2.

The other options are not as good as options B and C, for the following reasons:

Option A: Increasing the score threshold would decrease the detection rate of fraudulent transactions, which is the opposite of the desired outcome. Increasing the score threshold would decrease the recall of the model, which is the proportion of actual positive cases that are correctly identified. Decreasing the recall would increase the number of false negatives, which are fraudulent transactions that are missed by the model. Increasing the score threshold would increase the precision of the model, which is the proportion of positive predictions that are actually correct. Increasing the precision would decrease the number of false positives, which are legitimate transactions that are flagged as fraudulent by the model. However, in this use case, the cost of false negatives is much higher than the cost of false positives, so increasing the score threshold is not a good option1.

Option D: Adding more negative examples to the training set would not improve the model performance, and could worsen the data imbalance. Negative examples are the instances that belong to the other class, which in this case are legitimate transactions. Legitimate transactions are usually abundant and dominant compared to fraudulent transactions, which can cause the model to be biased towards the majority class and fail to learn the characteristics of the minority class. Adding more negative examples would exacerbate this problem, and decrease the detection rate of the fraudulent transactions2.

Option E: Reducing the maximum number of node hours for training would not improve the model performance, and could limit the model optimization. Node hours are the units of computation that are used to train an AutoML model. The maximum number of node hours is a parameter that determines the upper limit of node hours that can be used for training. Reducing the maximum number of node hours would reduce the training time and cost, but also the model quality and accuracy. Reducing the maximum number of node hours would limit the number of iterations, trials, and evaluations that the model can perform, and prevent the model from finding the optimal hyperparameters and architecture3.

References:

Preparing for Google Cloud Certification: Machine Learning Engineer, Course 5: Responsible AI, Week 4: Evaluation

Google Cloud Professional Machine Learning Engineer Exam Guide, Section 2: Developing high-quality ML models, 2.2 Handling imbalanced data

Official Google Cloud Certified Professional Machine Learning Engineer Study Guide, Chapter 4: Low-code ML Solutions, Section 4.3: AutoML

Understanding the score threshold slider

Handling imbalanced data sets in machine learning

AutoML Vision pricing

 A TPU VM is a virtual machine that has direct access to a Cloud TPU device. TPU VMs provide a simpler and more flexible way to use Cloud TPUs, as they eliminate the need for a separate host VM and network setup. TPU VMs also support interactive debugging tools such as TensorFlow Debugger (tfdbg) and Python Debugger (pdb), which can help researchers develop and troubleshoot complex models. A v3-8 TPU VM has 8 TPU cores, which can provide high performance and scalability for training large models. SSHing into the TPU VM allows the user to run and debug the TensorFlow code directly on the TPU device, without any network overhead or data transfer issues. References:

1: TPU VMs Overview

2: TPU VMs Quickstart

3: Debugging TensorFlow Models on Cloud TPUs

To configure a model retraining policy that minimizes cost, you should follow these steps:

Download the weather data each week, and download the flu data each month. This way, you can keep your data up to date with the latest information available, without downloading unnecessary or redundant data.

Deploy the model to a Vertex AI endpoint with feature drift monitoring. This feature allows you to detect when the distribution of the input data changes significantly from the training data, which could affect the model performance1.

Retrain the model if a monitoring alert is detected. This way, you can update your model only when needed, instead of retraining it on a fixed schedule, which could incur more cost and time.

References:

1: Monitor models for feature drift | Vertex AI | Google Cloud

 The best option for determining how often to retrain your model to maintain a high level of performance while minimizing cost is to run training-serving skew detection batch jobs every few days. Training-serving skew refers to the discrepancy between the distributions of the features in the training dataset and the serving data. This can cause the model to perform poorly on the new data, as it is not representative of the data that the model was trained on. By running training-serving skew detection batch jobs, you can monitor the changes in the feature distributions over time, and identify when the skew becomes significant enough to affect the model performance. If skew is detected, you can send the most recent serving data to the labeling service, and use the labeled data to retrain your model. This option has the following benefits:

It allows you to retrain your model only when necessary, based on the actual data changes, rather than on a fixed schedule or a heuristic. This can save you the cost of the labeling service and the retraining process, and also avoid overfitting or underfitting your model.

It leverages the existing tools and frameworks for training-serving skew detection, such as TensorFlow Data Validation (TFDV) and Vertex Data Labeling. TFDV is a library that can compute and visualize descriptive statistics for your datasets, and compare the statistics across different datasets. Vertex Data Labeling is a service that can label your data with high quality and low latency, using either human labelers or automated labelers.

It integrates well with the MLOps practices, such as continuous integration and continuous delivery (CI/CD), which can automate the workflow of running the skew detection jobs, sending the data to the labeling service, retraining the model, and deploying the new model version.

The other options are less optimal for the following reasons:

Option A: Training an anomaly detection model on the training dataset, and running all incoming requests through this model, introduces additional complexity and overhead. This option requires building and maintaining a separate model for anomaly detection, which can be challenging and time-consuming. Moreover, this option requires running the anomaly detection model on every request, which can increase the latency and resource consumption of the prediction service. Additionally, this option may not capture the subtle changes in the feature distributions that can affect the model performance, as anomalies are usually defined as rare or extreme events.

Option B: Identifying temporal patterns in your model’s performance over the previous year, and creating a schedule for sending serving data to the labeling service for the next year, introduces additional assumptions and risks. This option requires analyzing the historical data and model performance, and finding the patterns that can explain the variations in the model performance over time. However, this can be difficult and unreliable, as the patterns may not be consistent or predictable, and may depend on various factors that are not captured by the data. Moreover, this option requires creating a schedule based on the past patterns, which may not reflect the future changes in the data or the environment. This can lead to either sending too much or too little data to the labeling service, resulting in either wasted cost or degraded performance.

Option C: Comparing the cost of the labeling service with the lost revenue due to model performance degradation over the past year, and adjusting the frequency of model retraining accordingly, introduces additional challenges and trade-offs. This option requires estimating the cost of the labeling service and the lost revenue due to model performance degradation, which can be difficult and inaccurate, as they may depend on various factors that are not easily quantifiable or measurable. Moreover, this option requires finding the optimal balance between the cost and the performance, which can be subjective and variable, as different stakeholders may have different preferences and expectations. Furthermore, this option may not account for the potential impact of the model performance degradation on other aspects of the business, such as customer satisfaction, retention, or loyalty.

Option A is incorrect because using AI Platform notebooks to perform a Lasso regression analysis on your model, which will eliminate features that do not provide a strong signal, is not a suitable way to determine which customer attribute has the most predictive power for each prediction served by the model. Lasso regression is a method of feature selection that applies a penalty to the coefficients of the linear model, and shrinks them to zero for irrelevant features1. However, this method assumes that the model is linear and additive, which may not be the case for a TensorFlow model. Moreover, this method does not provide feature attributions for each prediction, but rather for the entire dataset.

Option B is incorrect because streaming prediction results to BigQuery, and using BigQuery’s CORR(X1, X2) function to calculate the Pearson correlation coefficient between each feature and the target variable, is not a valid way to determine which customer attribute has the most predictive power for each prediction served by the model. The Pearson correlation coefficient is a measure of the linear relationship between two variables, ranging from -1 to 12. However, this method does not account for the interactions between features or the non-linearity of the model. Moreover, this method does not provide feature attributions for each prediction, but rather for the entire dataset.

Option C is correct because using the AI Explanations feature on AI Platform, and submitting each prediction request with the ‘explain’ keyword to retrieve feature attributions using the sampled Shapley method, is the best way to determine which customer attribute has the most predictive power for each prediction served by the model. AI Explanations is a service that allows you to get feature attributions for your deployed models on AI Platform3. Feature attributions are values that indicate how much each feature contributed to the prediction for a given instance4. The sampled Shapley method is a technique that uses the Shapley value, a game-theoretic concept, to measure the contribution of each feature to the prediction5. By using AI Explanations, you can get feature attributions for each prediction request, and identify the most important features for each customer.

Option D is incorrect because using the What-If tool in Google Cloud to determine how your model will perform when individual features are excluded, and ranking the feature importance in order of those that caused the most significant performance drop when removed from the model, is not a practical way to determine which customer attribute has the most predictive power for each prediction served by the model. The What-If tool is a tool that allows you to visualize and analyze your ML models and datasets. However, this method requires manually editing or removing features for each instance, and observing the change in the prediction. This method is not scalable or efficient, and may not capture the interactions between features or the non-linearity of the model.

References:

Lasso regression

Pearson correlation coefficient

AI Explanations overview

Feature attributions

Sampled Shapley method

[What-If tool overview]

Cloud Vision API is a service that allows you to analyze images using pre-trained machine learning models1. You can use Cloud Vision API to perform various tasks, such as face detection, text extraction, logo recognition, and object localization1. Object localization is a feature that allows you to detect multiple objects in an image and draw bounding boxes around them2. You can also get the labels and confidence scores for each detected object2.

By sending user-submitted images to the Cloud Vision API, you can use object localization to identify all objects in the image and compare the results against a list of animals. You can use the OBJECT_LOCALIZATION feature type in the AnnotateImageRequest to request object localization3. You can then use the localizedObjectAnnotations field in the AnnotateImageResponse to get the list of detected objects, their labels, and their confidence scores. You can compare the labels with a predefined list of animals, such as dogs, cats, birds, etc., and determine whether the image has an animal or not.

This option is the best for your scenario, because it allows you to automatically and in near real time detect whether each uploaded photo has an animal, without requiring any manual labeling, model training, or model deployment. You can also prioritize time and minimize cost of your application development and deployment, as you can use the Cloud Vision API as a ready-to-use service, without needing any machine learning expertise or infrastructure.

The other options are not suitable for your scenario, because they either require manual labeling, model training, or model deployment, which would increase the time and cost of your application development and deployment, or they use object detection models, which are more complex and computationally expensive than object localization models, and are not necessary for your simple task of detecting whether an image has an animal or not.

References:

Cloud Vision API | Google Cloud

Object localization | Cloud Vision API | Google Cloud

AnnotateImageRequest | Cloud Vision API | Google Cloud

[AnnotateImageResponse | Cloud Vision API | Google Cloud]

A random forest is an ensemble learning method that consists of many decision trees. It can be used for both regression and classification tasks. A random forest classification model can predict the probability of churn for each customer by assigning them to different classes, such as high-risk, medium-risk, or low-risk. A random forest model can also generate feature importances, which measure how much each feature contributes to the prediction. Feature importances can help interpret the model and understand what factors influence customer churn. Vertex AI Workbench is an integrated development environment (IDE) that allows you to create and run Jupyter notebooks on Google Cloud. You can use Vertex AI Workbench to build a random forest classification model in Python, using libraries such as scikit-learn or TensorFlow. You can also configure the model to generate feature importances after the model is trained, and visualize them using plots or tables. This solution can help you build an interpretable model for customer churn prediction, and use the results to design marketing campaigns that target at-risk customers. References:

Random Forests | scikit-learn

Vertex AI Workbench | Google Cloud

Interpreting Random Forests | Towards Data Science

Feature attribution helps to determine how each feature influences predictions, essential for identifying bias. Vertex AI’s built-in explainability tools provide insights without altering the model’s feature space. Model monitoring (Option A) detects distributional drift rather than feature influence. Options B and D do not directly address the request to explain model decisions or provide fairness insights.

=================

The best option for scaling a Vertex AI endpoint efficiently when the demand increases in the future, using a scikit-learn model that is deployed to a Vertex AI endpoint and tested on live production traffic, is to configure an appropriate minReplicaCount value based on expected baseline traffic. This option allows you to leverage the power and simplicity of Vertex AI to automatically scale your endpoint resources according to the traffic patterns. Vertex AI is a unified platform for building and deploying machine learning solutions on Google Cloud. Vertex AI can deploy a trained model to an online prediction endpoint, which can provide low-latency predictions for individual instances. Vertex AI can also provide various tools and services for data analysis, model development, model deployment, model monitoring, and model governance. A minReplicaCount value is a parameter that specifies the minimum number of replicas that the endpoint must always have, regardless of the load. A minReplicaCount value can help you ensure that the endpoint has enough resources to handle the expected baseline traffic, and avoid high latency or errors. By configuring an appropriate minReplicaCount value based on expected baseline traffic, you can scale your endpoint efficiently when the demand increases in the future. You can set the minReplicaCount value when you deploy the model to the endpoint, or update it later. Vertex AI will automatically scale up or down the number of replicas within the range of the minReplicaCount and maxReplicaCount values, based on the target utilization percentage and the autoscaling metric1.

The other options are not as good as option B, for the following reasons:

Option A: Deploying two models to the same endpoint and distributing requests among them evenly would not allow you to scale your endpoint efficiently when the demand increases in the future, and could increase the complexity and cost of the deployment process. A model is a resource that represents a machine learning model that you can use for prediction. A model can have one or more versions, which are different implementations of the same model. A model version can help you experiment and iterate on your model, and improve the model performance and accuracy. An endpoint is a resource that provides the service endpoint (URL) you use to request the prediction. An endpoint can have one or more deployed models, which are instances of model versions that are associated with physical resources. A deployed model can help you serve online predictions with low latency, and scale up or down based on the traffic. By deploying two models to the same endpoint and distributing requests among them evenly, you can create a load balancing mechanism that can distribute the traffic across the models, and reduce the load on each model. However, deploying two models to the same endpoint and distributing requests among them evenly would not allow you to scale your endpoint efficiently when the demand increases in the future, and could increase the complexity and cost of the deployment process. You would need to write code, create and configure the two models, deploy the models to the same endpoint, and distribute the requests among them evenly. Moreover, this option would not use the autoscaling feature of Vertex AI, which can automatically adjust the number of replicas based on the traffic patterns, and provide various benefits, such as optimal resource utilization, cost savings, and performance improvement2.

Option C: Setting the target utilization percentage in the autoscalingMetricSpecs configuration to a higher value would not allow you to scale your endpoint efficiently when the demand increases in the future, and could cause errors or poor performance. A target utilization percentage is a parameter that specifies the desired utilization level of each replica. A target utilization percentage can affect the speed and accuracy of the autoscaling process. A higher target utilization percentage can help you reduce the number of replicas, but it can also cause high latency, low throughput, or resource exhaustion. By setting the target utilization percentage in the autoscalingMetricSpecs configuration to a higher value, you can increase the utilization level of each replica, and save some resources. However, setting the target utilization percentage in the autoscalingMetricSpecs configuration to a higher value would not allow you to scale your endpoint efficiently when the demand increases in the future, and could cause errors or poor performance. You would need to write code, create and configure the autoscalingMetricSpecs, and set the target utilization percentage to a higher value. Moreover, this option would not ensure that the endpoint has enough resources to handle the expected baseline traffic, which could cause high latency or errors1.

Option D: Changing the model’s machine type to one that utilizes GPUs would not allow you to scale your endpoint efficiently when the demand increases in the future, and could increase the complexity and cost of the deployment process. A machine type is a parameter that specifies the type of virtual machine that the prediction service uses for the deployed model. A machine type can affect the speed and accuracy of the prediction process. A machine type that utilizes GPUs can help you accelerate the computation and processing of the prediction, and handle more prediction requests at the same time. By changing the model’s machine type to one that utilizes GPUs, you can improve the prediction performance and efficiency of your model. However, changing the model’s machine type to one that utilizes GPUs would not allow you to scale your endpoint efficiently when the demand increases in the future, and could increase the complexity and cost of the deployment process. You would need to write code, create and configure the model, deploy the model to the endpoint, and change the machine type to one that utilizes GPUs. Moreover, this option would not use the autoscaling feature of Vertex AI, which can automatically adjust the number of replicas based on the traffic patterns, and provide various benefits, such as optimal resource utilization, cost savings, and performance improvement2.

References:

Configure compute resources for prediction | Vertex AI | Google Cloud

Deploy a model to an endpoint | Vertex AI | Google Cloud

According to the official exam guide1, one of the skills assessed in the exam is to “design, build, and productionalize ML models to solve business challenges using Google Cloud technologies”. The Vertex AI Vision Occupancy Analytics model2 is a specialized pre-built vision model that lets you count people or vehicles given specific inputs you add in video frames. It provides advanced features such as active zones counting, line crossing counting, and dwelling detection. This model is suitable for the use case of detecting the number of customers waiting for service in near real time. You can easily create and deploy an occupancy analytics application using Vertex AI Vision3. The other options are not relevant or optimal for this scenario. References:

Professional ML Engineer Exam Guide

Occupancy analytics guide

Create an occupancy analytics app with BigQuery forecasting

Google Professional Machine Learning Certification Exam 2023

Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

Option A is incorrect because Vertex AI Pipelines and App Engine do not meet all the requirements of the system. Vertex AI Pipelines is a service that allows you to create, run, and manage ML workflows using TensorFlow Extended (TFX) components or custom components1. App Engine is a service that allows you to build and deploy scalable web applications using standard or flexible environments2. However, App Engine does not support Docker containers in the standard environment, and does not provide a dedicated service for online prediction and monitoring of ML models3.

Option B is correct because Vertex AI Pipelines, Vertex AI Prediction, and Vertex AI Model Monitoring meet all the requirements of the system. Vertex AI Prediction is a service that allows you to deploy and serve ML models for online or batch prediction, with support for autoscaling and custom containers4. Vertex AI Model Monitoring is a service that allows you to monitor the performance and fairness of your deployed models, and get alerts for any issues or anomalies5.

Option C is incorrect because Cloud Composer, BigQuery ML, and Vertex AI Prediction do not meet all the requirements of the system. Cloud Composer is a service that allows you to create, schedule, and manage workflows using Apache Airflow. BigQuery ML is a service that allows you to create and use ML models within BigQuery using SQL queries. However, BigQuery ML does not support custom containers, and Vertex AI Prediction does not support scheduled model retraining or model monitoring.

Option D is incorrect because Cloud Composer, Vertex AI Training with custom containers, and App Engine do not meet all the requirements of the system. Vertex AI Training is a service that allows you to train ML models using built-in algorithms or custom containers. However, Vertex AI Training does not support online prediction or model monitoring, and App Engine does not support Docker containers in the standard environment or online prediction and monitoring of ML models3.

References:

Vertex AI Pipelines overview

App Engine overview

Choosing an App Engine environment

Vertex AI Prediction overview

Vertex AI Model Monitoring overview

[Cloud Composer overview]

[BigQuery ML overview]

[BigQuery ML limitations]

[Vertex AI Training overview]

 AutoML Natural Language is a service that allows you to build and train custom natural language models without writing code. You can use AutoML Natural Language to perform sentiment analysis with custom categories, such as positive, negative, or neutral. You can also use pre-trained models or transfer learning to leverage existing knowledge and reduce the amount of data required to train a model from scratch. AutoML Natural Language provides a user-friendly interface and a powerful AutoML engine that optimizes your model for high predictive performance.

Cloud Natural Language API is a service that provides pre-trained models for common natural language tasks, such as sentiment analysis, entity analysis, and syntax analysis. However, it does not allow you to customize the categories or use your own data for training.

AI Hub pre-made Jupyter Notebooks are interactive documents that contain code, text, and visualizations for various machine learning scenarios. However, they require some coding skills and data preparation to use them effectively.

AI Platform Training built-in algorithms are pre-configured machine learning algorithms that you can use to train models on AI Platform. However, they do not support sentiment analysis as a natural language task.

References:

AutoML Natural Language documentation

Cloud Natural Language API documentation

AI Hub documentation

AI Platform Training documentation

The best option for reducing pipeline execution time and cost, while also minimizing pipeline changes, is to enable caching for the pipeline job, and disable caching for the model training step. This option allows you to leverage the power and simplicity of Vertex AI Pipelines to reuse the output of the data preprocessing step, and avoid unnecessary recomputation. Vertex AI Pipelines is a service that can orchestrate machine learning workflows using Vertex AI. Vertex AI Pipelines can run preprocessing and training steps on custom Docker images, and evaluate, deploy, and monitor the machine learning model. Caching is a feature of Vertex AI Pipelines that can store and reuse the output of a pipeline step, and skip the execution of the step if the input parameters and the code have not changed. Caching can help you reduce the pipeline execution time and cost, as you do not need to re-run the same step with the same input and code. Caching can also help you minimize the pipeline changes, as you do not need to add or remove any pipeline steps or parameters. By enabling caching for the pipeline job, and disabling caching for the model training step, you can create a Vertex AI pipeline that includes two steps. The first step preprocesses 10 TB data, completes in about 1 hour, and saves the result in a Cloud Storage bucket. The second step uses the processed data to train a model. You can update the model’s code to allow you to test different algorithms, and run the pipeline job with caching enabled. The pipeline job will reuse the output of the data preprocessing step from the cache, and skip the execution of the step. The pipeline job will run the model training step with the updated code, and disable the caching for the step. This way, you can reduce the pipeline execution time and cost, while also minimizing pipeline changes1.

The other options are not as good as option D, for the following reasons:

Option A: Adding a pipeline parameter and an additional pipeline step, depending on the parameter value, the pipeline step conducts or skips data preprocessing and starts model training, would require more skills and steps than enabling caching for the pipeline job, and disabling caching for the model training step. A pipeline parameter is a variable that can be used to control the input or output of a pipeline step. A pipeline parameter can help you customize the pipeline logic and behavior, and experiment with different values. An additional pipeline step is a new instance of a pipeline component that can perform a part of the pipeline workflow, such as data preprocessing or model training. An additional pipeline step can help you extend the pipeline functionality and complexity, and handle different scenarios. However, adding a pipeline parameter and an additional pipeline step, depending on the parameter value, the pipeline step conducts or skips data preprocessing and starts model training, would require more skills and steps than enabling caching for the pipeline job, and disabling caching for the model training step. You would need to write code, define the pipeline parameter, create the additional pipeline step, implement the conditional logic, and compile and run the pipeline. Moreover, this option would not reuse the output of the data preprocessing step from the cache, but rather from the Cloud Storage bucket, which can increase the data transfer and access costs1.

Option B: Creating another pipeline without the preprocessing step, and hardcoding the preprocessed Cloud Storage file location for model training, would require more skills and steps than enabling caching for the pipeline job, and disabling caching for the model training step. A pipeline without the preprocessing step is a pipeline that only includes the model training step, and uses the preprocessed data from the Cloud Storage bucket as the input. A pipeline without the preprocessing step can help you avoid running the data preprocessing step every time, and reduce the pipeline execution time and cost. However, creating another pipeline without the preprocessing step, and hardcoding the preprocessed Cloud Storage file location for model training, would require more skills and steps than enabling caching for the pipeline job, and disabling caching for the model training step. You would need to write code, create a new pipeline, remove the preprocessing step, hardcode the Cloud Storage file location, and compile and run the pipeline. Moreover, this option would not reuse the output of the data preprocessing step from the cache, but rather from the Cloud Storage bucket, which can increase the data transfer and access costs. Furthermore, this option would create another pipeline, which can increase the maintenance and management costs1.

Option C: Configuring a machine with more CPU and RAM from the compute-optimized machine family for the data preprocessing step, would not reduce the pipeline execution time and cost, while also minimizing pipeline changes, but rather increase the pipeline execution cost and complexity. A machine with more CPU and RAM from the compute-optimized machine family is a virtual machine that has a high ratio of CPU cores to memory, and can provide high performance and scalability for compute-intensive workloads. A machine with more CPU and RAM from the compute-optimized machine family can help you optimize the data preprocessing step, and reduce the pipeline execution time. However, configuring a machine with more CPU and RAM from the compute-optimized machine family for the data preprocessing step, would not reduce the pipeline execution time and cost, while also minimizing pipeline changes, but rather increase the pipeline execution cost and complexity. You would need to write code, configure the machine type parameters for the data preprocessing step, and compile and run the pipeline. Moreover, this option would increase the pipeline execution cost, as machines with more CPU and RAM from the compute-optimized machine family are more expensive than machines with less CPU and RAM from other machine families. Furthermore, this option would not reuse the output of the data preprocessing step from the cache, but rather re-run the data preprocessing step every time, which can increase the pipeline execution time and cost1.

References:

Preparing for Google Cloud Certification: Machine Learning Engineer, Course 3: Production ML Systems, Week 3: MLOps

Google Cloud Professional Machine Learning Engineer Exam Guide, Section 3: Scaling ML models in production, 3.2 Automating ML workflows

Official Google Cloud Certified Professional Machine Learning Engineer Study Guide, Chapter 6: Production ML Systems, Section 6.4: Automating ML Workflows

Vertex AI Pipelines

Caching

Pipeline parameters

Machine types

According to the official exam guide1, one of the skills assessed in the exam is to “configure and optimize model monitoring jobs”. The Vertex AI Model Monitoring documentation states that “to reduce the cost of model monitoring, you can configure the sample rate of the requests that are logged and analyzed by model monitoring”. Therefore, decreasing the sample_rate parameter in the Randomsampleconfig of the monitoring job would reduce the model monitoring cost while continuing to quickly detect drift. The other options are not relevant or optimal for this scenario. References:

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Professional ML Engineer Exam Guide

Google Professional Machine Learning Certification Exam 2023

Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

[Vertex AI Model Monitoring]

Kubeflow Pipelines allows for efficient use of compute resources through parallel task execution and caching, which eliminates redundant executions1. By enabling caching in all the steps of the Kubeflow pipeline, you can avoid re-running the same steps when you execute the pipeline multiple times. This can significantly speed up the pipeline execution and reduce your development time without incurring additional costs

Federated learning is a machine learning technique that enables organizations to train AI models on decentralized data without centralizing or sharing it1. It allows data privacy, continual learning, and better performance on end-user devices2. Federated learning works by sending the model parameters to the devices, where they are updated locally on the device’s data, and then aggregating the updated parameters on a central server to form a global model3. This way, the data never leaves the device and the model can learn from a large and diverse dataset.

Federated learning is suitable for the use case of building an ML-based biometric authentication for the bank’s mobile app that verifies a customer’s identity based on their fingerprint. Fingerprints are considered highly sensitive personal information and cannot be downloaded and stored into the bank databases. By using federated learning, the bank can train and deploy an ML model that can recognize fingerprints without compromising the data privacy of the customers. The model can also adapt to the variations and changes in the fingerprints over time and improve its accuracy and reliability. Therefore, federated learning is the best learning strategy for this use case.

To avoid creating or reinforcing unfair bias in the model, you should collect a representative sample of production traffic to build the training dataset, and conduct fairness tests across sensitive categories and demographics on the trained model. A representative sample is one that reflects the true distribution of the population, and does not over- or under-represent any group. A random sample is a simple way to obtain a representative sample, as it ensures that every data point has an equal chance of being selected. A stratified sample is another way to obtain a representative sample, as it ensures that every subgroup has a proportional representation in the sample. However, a stratified sample requires prior knowledge of the subgroups and their sizes, which may not be available or easy to obtain. Therefore, a random sample is a more feasible option in this case. A fairness test is a way to measure and evaluate the potential bias and discrimination of the model, based on different categories and demographics, such as age, gender, race, etc. A fairness test can help you identify and mitigate any unfair outcomes or impacts of the model, and ensure that the model treats all groups fairly and equitably. A fairness test can be conducted using various methods and tools, such as confusion matrices, ROC curves, fairness indicators, etc. References: The answer can be verified from official Google Cloud documentation and resources related to data sampling and fairness testing.

Sampling data | BigQuery

Fairness Indicators | TensorFlow

What-if Tool | TensorFlow

According to the web search results, RunInference API1 is a feature of Apache Beam that enables you to run models as part of your pipeline in a way that is optimized for machine learning inference. RunInference API supports features like batching, caching, and model reloading. RunInference API can be used with various frameworks, such as TensorFlow, PyTorch, Sklearn, XGBoost, ONNX, and TensorRT1. Dataflow2 is a fully managed service for running Apache Beam pipelines on Google Cloud. Dataflow handles the provisioning and management of the compute resources, as well as the optimization and execution of the pipelines. Therefore, option D is the best way to reconfigure the architecture for the given use case, as it allows you to use the RunInference API with watchFilePattern in a Dataflow job that wraps around the model and serves predictions. This way, you can minimize prediction latency and the effort required to update the model, as the RunInference API will automatically reload the model from the Cloud Storage bucket whenever there is a change in the model file1. The other options are not relevant or optimal for this scenario. References:

RunInference API

Dataflow

Google Professional Machine Learning Certification Exam 2023

Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

Monitoring model performance is an essential part of production readiness, as it allows the team to detect and address any issues that may arise after deployment, such as data drift, model degradation, or errors.

Other Options:

A. Ensuring that training is reproducible is important for model development, but not necessarily for production readiness. Reproducibility helps the team to track and compare different experiments, but it does not guarantee that the model will perform well in production.

B. Ensuring that all hyperparameters are tuned is also important for model development, but not sufficient for production readiness. Hyperparameter tuning helps the team to find the optimal configuration for the model, but it does not account for the dynamic and changing nature of the production environment.

D. Ensuring that feature expectations are captured in the schema is a part of testing features and data, which the team has already done. The schema defines the expected format, type, and range of the features, and helps the team to validate and preprocess the data.