Catherine D. Schuman, Steven R. Young and Bryan P. Maldonao and Brian C. Kaul

October, 2021

12th International Green and Sustainable Computing Conference (IGSC)

https://www.rit.edu/kgcoe/brainlab/aiattheedge

View Article

Abstract

Extremely low power neuromorphic systems are well-suited for deployment to the edge for many applications. In many use cases of neuromorphic computing for control, a spiking neural network is trained off-line using a simulation and then deployed to a neuromorphic system at the edge, where it will operate without ongoing training or learning. However, it may be desirable to continue training or learning at the edge to refine or adapt to the real-world system. In this work, we propose an approach for performing real-time evolutionary optimization for spiking neural networks for neuromorphic deployment at the edge. In particular, we propose a combination of simulation and real-world evaluations, along with feedback from the real-world environment, to train spiking neural networks for continuous deployment to the edge. We show that the real-time evolution at the edge approach achieves comparable performance to an evolution approach that requires constant evaluation in the real-world environment.

Citation Information

Text

author       C. D. Schuman and S. R. Young and B. P. Maldonado and B. C. Kaul
title        Real-Time Evolution and Deployment of Neuromorphic Computing at The Edge
booktitle    12th International Green and Sustainable Computing Conference (IGSC)
year         2021
pages        1-8
organization IEEE

Bibtex

@INPROCEEDINGS{sym:21:rte,
    author = "C. D. Schuman and S. R. Young and B. P. Maldonado and B. C. Kaul",
    title = "Real-Time Evolution and Deployment of Neuromorphic Computing at The Edge",
    booktitle = "12th International Green and Sustainable Computing Conference (IGSC)",
    year = "2021",
    pages = "1-8",
    organization = "IEEE"
}