Google Google Certifications PROFESSIONAL-MACHINE-LEARNING-ENGINEER Questions & Answers

• Question 11:

  You have trained a DNN regressor with TensorFlow to predict housing prices using a set of predictive features. Your default precision is tf.float64, and you use a standard TensorFlow estimator:

  

  Your model performs well, but just before deploying it to production, you discover that your current serving latency is 10ms @ 90 percentile and you currently serve on CPUs. Your production requirements expect a model latency of 8ms @ 90 percentile. You're willing to accept a small decrease in performance in order to reach the latency requirement.

  Therefore your plan is to improve latency while evaluating how much the model's prediction decreases. What should you first try to quickly lower the serving latency?

  A. Switch from CPU to GPU serving.

  B. Apply quantization to your SavedModel by reducing the floating point precision to tf.float16.

  C. Increase the dropout rate to 0.8 and retrain your model.

  D. Increase the dropout rate to 0.8 in _PREDICT mode by adjusting the TensorFlow Serving parameters.

  Correct Answer: A

  https://www.tensorflow.org/lite/performance/post_training_quantization#float16_quantization

• Question 12:

  You are developing an image recognition model using PyTorch based on ResNet50 architecture. Your code is working fine on your local laptop on a small subsample. Your full dataset has 200k labeled images. You want to quickly scale your training workload while minimizing cost. You plan to use 4 V100 GPUs. What should you do?

  A. Create a Google Kubernetes Engine cluster with a node pool that has 4 V100 GPUs. Prepare and submit a TFJob operator to this node pool.

  B. Create a Vertex AI Workbench user-managed notebooks instance with 4 V100 GPUs, and use it to train your model.

  C. Package your code with Setuptools, and use a pre-built container. Train your model with Vertex AI using a custom tier that contains the required GPUs.

  D. Configure a Compute Engine VM with all the dependencies that launches the training. Train your model with Vertex AI using a custom tier that contains the required GPUs.

  Correct Answer: C

  "Vertex AI provides flexible and scalable hardware and secured infrastructure to train PyTorch based deep learning models with pre-built containers and custom containers. (...) use PyTorch ResNet-50 as the example model and train it on ImageNet validation data (50K images) to measure the training performance for different training strategies": https://cloud.google.com/blog/products/ai-machine-learning/efficient-pytorch-training-with-vertex-ai

• Question 13:

  You have developed an ML model to detect the sentiment of users' posts on your company's social media page to identify outages or bugs. You are using Dataflow to provide real-time predictions on data ingested from Pub/Sub. You plan to have multiple training iterations for your model and keep the latest two versions live after every run. You want to split the traffic between the versions in an 80:20 ratio, with the newest model getting the majority of the traffic. You want to keep the pipeline as simple as possible, with minimal management required. What should you do?

  A. Deploy the models to a Vertex AI endpoint using the traffic-split=0=80, PREVIOUS_MODEL_ID=20 configuration.

  B. Wrap the models inside an App Engine application using the --splits PREVIOUS_VERSION=0.2, NEW_VERSION=0.8 configuration

  C. Wrap the models inside a Cloud Run container using the REVISION1=20, REVISION2=80 revision configuration.

  D. Implement random splitting in Dataflow using beam.Partition() with a partition function calling a Vertex AI endpoint.

  Correct Answer: A

  The recommended approach to achieve the desired outcome would be to deploy the ML models to a Vertex AI endpoint and configure the traffic splitting using the traffic-split parameter. The traffic-split parameter enables you to split traffic between multiple versions of a model based on a percentage split. In this case, the newest model should receive the majority of the traffic, which can be achieved by setting the traffic-split parameter to 0=80. The previous version of the model should receive the remaining 20% of the traffic, which can be achieved by setting the PREVIOUS_MODEL_ID parameter to 20.

• Question 14:

  You have built a model that is trained on data stored in Parquet files. You access the data through a Hive table hosted on Google Cloud. You preprocessed these data with PySpark and exported it as a CSV file into Cloud Storage. After preprocessing, you execute additional steps to train and evaluate your model. You want to parametrize this model training in Kubeflow Pipelines. What should you do?

  A. Remove the data transformation step from your pipeline.

  B. Containerize the PySpark transformation step, and add it to your pipeline.

  C. Add a ContainerOp to your pipeline that spins a Dataproc cluster, runs a transformation, and then saves the transformed data in Cloud Storage.

  D. Deploy Apache Spark at a separate node pool in a Google Kubernetes Engine cluster. Add a ContainerOp to your pipeline that invokes a corresponding transformation job for this Spark instance.

  Correct Answer: C

  https://kubeflow-pipelines.readthedocs.io/en/stable/source/kfp.dsl.html#kfp.dsl.ContainerOp https://medium.com/@vignesh093/running-preprocessing-and-ml-workflow-in-kubeflow-with-google-dataproc-84103a9ef67e

• Question 15:

  You work for a magazine publisher and have been tasked with predicting whether customers will cancel their annual subscription. In your exploratory data analysis, you find that 90% of individuals renew their subscription every year, and only 10% of individuals cancel their subscription. After training a NN Classifier, your model predicts those who cancel their subscription with 99% accuracy and predicts those who renew their subscription with 82% accuracy. How should you interpret these results?

  A. This is not a good result because the model should have a higher accuracy for those who renew their subscription than for those who cancel their subscription.

  B. This is not a good result because the model is performing worse than predicting that people will always renew their subscription.

  C. This is a good result because predicting those who cancel their subscription is more difficult, since there is less data for this group.

  D. This is a good result because the accuracy across both groups is greater than 80%.

  Correct Answer: C

• Question 16:

  You work for a retailer that sells clothes to customers around the world. You have been tasked with ensuring that ML models are built in a secure manner. Specifically, you need to protect sensitive customer data that might be used in the models. You have identified four fields containing sensitive data that are being used by your data science team: AGE, IS_EXISTING_CUSTOMER, LATITUDE_LONGITUDE, and SHIRT_SIZE. What should you do with the data before it is made available to the data science team for training purposes?

  A. Tokenize all of the fields using hashed dummy values to replace the real values.

  B. Use principal component analysis (PCA) to reduce the four sensitive fields to one PCA vector.

  C. Coarsen the data by putting AGE into quantiles and rounding LATITUDE_LONGTTUDE into single precision. The other two fields are already as coarse as possible.

  D. Remove all sensitive data fields, and ask the data science team to build their models using non-sensitive data.

  Correct Answer: A

  https://cloud.google.com/blog/products/identity-security/take-charge-of-your-data-how-tokenization-makes-data-usable-without-sacrificing-privacy

• Question 17:

  You work for a company that manages a ticketing platform for a large chain of cinemas. Customers use a mobile app to search for movies they're interested in and purchase tickets in the app. Ticket purchase requests are sent to Pub/Sub and are processed with a Dataflow streaming pipeline configured to conduct the following steps:

  1.

  Check for availability of the movie tickets at the selected cinema.

  2.

  Assign the ticket price and accept payment.

  3.

  Reserve the tickets at the selected cinema.

  4.

  Send successful purchases to your database.

  Each step in this process has low latency requirements (less than 50 milliseconds). You have developed a logistic regression model with BigQuery ML that predicts whether offering a promo code for free popcorn increases the chance of a ticket purchase, and this prediction should be added to the ticket purchase process. You want to identify the simplest way to deploy this model to production while adding minimal latency. What should you do?

  A. Run batch inference with BigQuery ML every five minutes on each new set of tickets issued.

  B. Export your model in TensorFlow format, and add a tfx_bsl.public.beam.RunInference step to the Dataflow pipeline.

  C. Export your model in TensorFlow format, deploy it on Vertex AI, and query the prediction endpoint from your streaming pipeline.

  D. Convert your model with TensorFlow Lite (TFLite), and add it to the mobile app so that the promo code and the incoming request arrive together in Pub/Sub.

  Correct Answer: D

  https://www.tensorflow.org/lite/guide

• Question 18:

  You work on a team in a data center that is responsible for server maintenance. Your management team wants you to build a predictive maintenance solution that uses monitoring data to detect potential server failures. Incident data has not been labeled yet. What should you do first?

  A. Train a time-series model to predict the machines' performance values. Configure an alert if a machine's actual performance values significantly differ from the predicted performance values.

  B. Develop a simple heuristic (e.g., based on z-score) to label the machines' historical performance data. Use this heuristic to monitor server performance in real time.

  C. Develop a simple heuristic (e.g., based on z-score) to label the machines' historical performance data. Train a model to predict anomalies based on this labeled dataset.

  D. Hire a team of qualified analysts to review and label the machines' historical performance data. Train a model based on this manually labeled dataset.

  Correct Answer: B

  https://developers.google.com/machine-learning/guides/rules-of-ml

• Question 19:

  You deployed an ML model into production a year ago. Every month, you collect all raw requests that were sent to your model prediction service during the previous month. You send a subset of these requests to a human labeling service to evaluate your model's performance. After a year, you notice that your model's performance sometimes degrades significantly after a month, while other times it takes several months to notice any decrease in performance. The labeling service is costly, but you also need to avoid large performance degradations. You want to determine how often you should retrain your model to maintain a high level of performance while minimizing cost. What should you do?

  A. Train an anomaly detection model on the training dataset, and run all incoming requests through this model. If an anomaly is detected, send the most recent serving data to the labeling service.

  B. Identify temporal patterns in your model's performance over the previous year. Based on these patterns, create a schedule for sending serving data to the labeling service for the next year.

  C. Compare the cost of the labeling service with the lost revenue due to model performance degradation over the past year. If the lost revenue is greater than the cost of the labeling service, increase the frequency of model retraining; otherwise, decrease the model retraining frequency.

  D. Run training-serving skew detection batch jobs every few days to compare the aggregate statistics of the features in the training dataset with recent serving data. If skew is detected, send the most recent serving data to the labeling service.

  Correct Answer: D

  https://cloud.google.com/blog/topics/developers-practitioners/monitor-models-training-serving-skew-vertex-aiew-vertex-aiandved=2ahUKEwiRg_aoj9n8AhWb7TgGHcGCDREQFnoECAwQAQandusg=AOvVaw197NneIJM0ra7fLq2zsOin

• Question 20:

  You work for an online publisher that delivers news articles to over 50 million readers. You have built an AI model that recommends content for the company's weekly newsletter. A recommendation is considered successful if the article is opened within two days of the newsletter's published date and the user remains on the page for at least one minute.

  All the information needed to compute the success metric is available in BigQuery and is updated hourly. The model is trained on eight weeks of data, on average its performance degrades below the acceptable baseline after five weeks, and training time is 12 hours. You want to ensure that the model's performance is above the acceptable baseline while minimizing cost. How should you monitor the model to determine when retraining is necessary?

  A. Use Vertex AI Model Monitoring to detect skew of the input features with a sample rate of 100% and a monitoring frequency of two days.

  B. Schedule a cron job in Cloud Tasks to retrain the model every week before the newsletter is created.

  C. Schedule a weekly query in BigQuery to compute the success metric.

  D. Schedule a daily Dataflow job in Cloud Composer to compute the success metric.

  Correct Answer: C

  https://cloud.google.com/blog/topics/developers-practitioners/continuous-model-evaluation-bigquery-ml-stored-procedures-and-cloud-scheduler