Tutorial 1
in
Workshop: 2nd On-Device Intelligence Workshop
TinyML Model Design (Igor Fedorov, Arm Research)
Abstract:
This talk will review the challenges associated with designing models that can be run on memory and compute constrained devices. We will then summarize some of the model design techniques which are particularly useful for TinyML applications, including pruning, quantization, and black-box / gradient-based neural architecture search.