Skip to main content

Island Model for Parallel Evolutionary Optimization of Spiking Neuromorphic Computing

by Catherine D Schuman, James Plank, Robert M Patton, Thomas E Potok
Publication Type
Conference Paper
Book Title
GECCO '19 Proceedings of the Genetic and Evolutionary Computation Conference Companion
Publication Date
Page Numbers
306 to 307
Publisher Location
New York, New York, United States of America
Conference Name
The Genetic and Evolutionary Computation Conference (GECCO 2019)
Conference Location
Prague, Czech Republic
Conference Sponsor
Conference Date

Parallel genetic algorithms (PGAs) can be used to accelerate optimization by exploiting large-scale computational resources. In this work, we describe a PGA framework for evolving spiking neural networks (SNNs) for neuromorphic hardware implementation. The PGA framework is based on an islands model with migration. We show that using this framework, better SNNs for neuromorphic systems can be evolved faster.