Google Professional Machine Learning Engineer exam dumps

Google Professional Machine Learning Engineer practice question 255 of 522

Professional Machine Learning Engineer. Professional level, Google Cloud. Free question with the correct answer and a full explanation.

Google Professional Machine Learning Engineer Question 255

Select 4Google Cloud Platform

Your organization wants to build a machine learning workflow to predict sales using tabular data. The team has decided to use AutoML for model training and prediction due to its ease of use. They also want to deploy the solution using Kubernetes Engine for scalability. Which of the following steps should you include in your workflow to achieve this?

  1. A

    Prepare your tabular dataset and upload it to a Cloud Storage bucket.

  2. B

    Use the Google Cloud Console or AutoML API to create, train, and evaluate your model.

  3. C

    Export the trained model from AutoML as a TensorFlow SavedModel format.

  4. D

    Deploy the trained model directly to Google Kubernetes Engine using a custom Docker image.

  5. E

    Use Vertex AI to create a serving endpoint for the AutoML model.

Show answer and explanation

Correct answers: A, B, C, D

Explanation

To integrate AutoML with Kubernetes Engine for deploying a tabular data prediction solution, you need to first prepare and upload the dataset to Cloud Storage for AutoML training. Once the model is trained using AutoML, it can be exported as a TensorFlow SavedModel and deployed to a Kubernetes Engine cluster using a custom Docker container. This approach ensures scalability and flexibility for your serving infrastructure. Using Vertex AI endpoints is not required because the deployment specifically targets Kubernetes Engine.

  • A. Correct.

    Correct. AutoML requires the dataset to be uploaded to a Cloud Storage bucket to train the model.

  • B. Correct.

    Correct. AutoML allows you to create, train, and evaluate your model using either the Google Cloud Console or the AutoML API.

  • C. Correct.

    Correct. After the model is trained in AutoML, it can be exported as a TensorFlow SavedModel, which is compatible with deployment workflows.

  • D. Correct.

    Correct. The trained model can be containerized using a custom Docker image and deployed to Google Kubernetes Engine for serving.

  • E. Incorrect.

    Incorrect. Vertex AI endpoints are not necessary in this context as the team wants to directly deploy the model to Kubernetes Engine for scalability.

Timed practice exam

Take a Google Professional Machine Learning Engineer practice test under exam conditions

60 questions in 120 minutes, drawn from this bank, with a score report and a per-question review when you finish.

Start timed exam

More Google Professional Machine Learning Engineer practice questions

  1. 256.Your team is tasked with building a machine learning model to predict customer churn using a...
  2. 257.Your company wants to deploy a machine learning model to predict customer churn using a tabular...
  3. 258.You are tasked with deploying a machine learning workflow for predicting customer churn using...
  4. 259.You are developing a machine learning model that requires distributed training due to the size of...
  5. 260.Your organization is building a machine learning pipeline to train a large neural network model on...
Back to the Google Professional Machine Learning Engineer exam dumps