Catherine D. Schuman, J. Parker Mitchell, Robert M. Patton, Thomas E. Potok and James S. Plank

March, 2020

NICE: Neuro-Inspired Computational Elements Workshop

https://niceworkshop.org/nice-2020/

View Article

Abstract

Designing and training an appropriate spiking neural network for neuromorphic deployment remains an open challenge in neuromorphic computing. In 2016, we introduced an approach for utilizing evolutionary optimization to address this challenge called Evolutionary Optimization for Neuromorphic Systems (EONS). In this work, we present an improvement to this approach that enables rapid prototyping of new applications of spiking neural networks in neuromorphic systems. We discuss the overall EONS framework and its improvements over the previous implementation. We present several case studies of how EONS can be used, including to train spiking neural networks for classification and control tasks, to train under hardware constraints, to evolve a reservoir for a liquid state machine, and to evolve smaller networks using multi-objective optimization.

Citation Information

Text

author     C. D. Schuman and J. P. Mitchell and R. M. Patton and T. E. Potok and J. S. Plank
title      Evolutionary Optimization for Neuromorphic Systems
booktitle  NICE: Neuro-Inspired Computational Elements Workshop
year       2020
where      http://neuromorphic.eecs.utk.edu/publications/2020-03-17-evolutionary-optimization-for-neuromorphic-systems

Bibtex

@INPROCEEDINGS{smp:20:eons,
    author = "C. D. Schuman and J. P. Mitchell and R. M. Patton and T. E. Potok and J. S. Plank",
    title = "Evolutionary Optimization for Neuromorphic Systems",
    booktitle = "NICE: Neuro-Inspired Computational Elements Workshop",
    year = "2020",
    where = "http://neuromorphic.eecs.utk.edu/publications/2020-03-17-evolutionary-optimization-for-neuromorphic-systems"
}