AIM311-R1: The right instance type in Amazon SageMaker, ft. Texas Instruments

Amazon SageMaker, a fully managed service for machine learning, offers several compute capabilities and instance types to meet the needs of your use case. In this session, we review the compute options available to you, including GPUs, CPUs, AWS Inferentia, Amazon SageMaker Neo, and Amazon Elastic Inference. We discuss best practices and key criteria to choose the right capabilities that meet the specific needs of your machine learning workload.