Machine Learning for Embedded Systems. 3 credits

Catalog description

This course introduces the methodologies and approaches for accommodating neural networks into resource-constrained edge computing. It focuses on the embedded systems and introduces techniques for developing energy/time efficient machine learning (ML) algorithms and models suitable for them. Topics covered include commonly used ML algorithms, ML model compression techniques, hardware-aware ML, and hardware and neural architecture co-design. The course also provides a comprehensive team-based research and development experience through projects and presentations. Offered by Electrical & Comp. Engineering . May not be repeated for credit.