Short Course: Architecture and Design Approaches to ML Hardware Acceleration: Edge and Mobile Environments
Marian Verhelst · 2024
Various applications demand more and more powerful machine inference in resource-scarce distributed devices, such as phones, watches, glasses, robots or drones. To allow intelligent applications at ultra-low energy and low latency, one needs customized processor architectures optimized for extreme edge applications. This need has resulted in the creation of a wide variety of novel hardware architectures, supported by HW-algorithm co-optimization methods. This talk will zoom into ML processor architectures for the edge, as well as tools for efficient mapping of ML algorithms onto such architectures.