Skip to Content

AI-900: Azure Machine Learning Compute Targets: What are they and how to choose them?

Learn what are compute targets in Azure Machine Learning, how they differ from each other, and how to choose the right one for your machine learning scenario.

Table of Contents

Question

You created a machine learning model and trained it. Now you want to run the model to predict data. Which compute target should you use?

A. Compute Clusters
B. Compute Instances
C. Inference Clusters

Answer

C. Inference Clusters

Explanation

Inference Clusters are used as deployment targets for predictive services that use your trained models.

The correct answer is C. Inference Clusters.

Inference clusters are compute targets that are used to run machine learning models to predict data. They are also known as Azure Machine Learning endpoints. Inference clusters are fully managed computes for real-time (managed online endpoints) or batch (managed batch endpoints) inference. They support GPU acceleration and autoscaling.

Compute clusters are compute targets that are used to train machine learning models on large datasets or perform distributed training. They are also known as Azure Machine Learning compute clusters. Compute clusters are single- or multi-node clusters that autoscale each time you submit a job.

Compute instances are compute targets that are used to develop and test machine learning models on a small amount of data. They are also known as Azure Machine Learning compute instances. Compute instances are cloud-based virtual machines that you can use as a workstation for data science tasks.

Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Fundamentals AI-900 exam and earn Microsoft Azure AI Fundamentals AI-900 certification.

Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump