Explanation:
Amazon SageMaker Inference Endpoints are designed to provide secure, scalable real-time model hosting for inference. This allows machine learning models to be deployed as endpoints that can serve predictions in real-time to applications. The other options describe different functionalities:
Ultimate access to all questions.
What is the primary purpose of Amazon SageMaker Inference Endpoints?
A
To visualize predictions made by machine learning models
B
To provide secure, scalable real-time model hosting for inference
C
To clean and preprocess raw datasets
D
To automate Jupyter notebook creation
No comments yet.