Skip to main content
SHARE
Publication

Evolutionary Optimization for Neuromorphic Systems...

by Catherine D Schuman, John P Mitchell, Robert M Patton, Thomas E Potok, James Plank
Publication Type
Conference Paper
Book Title
NICE '20: Proceedings of the Neuro-inspired Computational Elements Workshop
Publication Date
Page Numbers
1 to 9
Publisher Location
United States of America
Conference Name
Neuro Inspired Computational Elements Workshop (NICE)
Conference Location
Heidelberg, Germany
Conference Sponsor
ACM
Conference Date
-

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.