Enabling tinyML by Expoliting Heterogenous Multi-Core AI Processing

TinyML strives for powerful machine inference in resource-scarce distributed devices. To allow intelligent applications at ultra-low energy and low latency, one needs 1.) compact compute and memory structures; 2.) which are used at very high utilization. This talk will introduce the benefits and challenges of such heterogeneous ML systems for intelligent edge devices, supported by practical examples for efficient deep inference.

TinyML strives for powerful machine inference in resource-scarce distributed devices. To allow intelligent applications at ultra-low energy and low latency, one needs 1.) compact compute and memory structures; 2.) which are used at very high utilization. This talk will introduce the benefits and challenges of such heterogeneous ML systems for intelligent edge devices, supported by practical examples for efficient deep inference.

IEEE-Affiliated Group Name: IEEE Circuits and Systems Society

URL: https://resourcecenter.cas.ieee.org/conferences/isicas-2022/CAS2022ISICAS0010.html