Catherine D. Shuman, Grant Bruer, Aaron R. Young, Mark Dean and James S. Plank

July, 2018

IJCNN: The International Joint Conference on Neural Networks

http://www.ecomp.poli.br/~wcci2018/

View Article

Abstract

Evolutionary optimization or genetic algorithms have been used to optimize a variety of neural network types, including spiking recurrent neural networks, and are attractive for many reasons. However, a key impediment to their widespread use is the potential for slow training times and failure to converge to a good fitness value in a reasonable amount of time. In this work, we evaluate the effect of different selection algorithms on the performance of an evolutionary optimization method for designing spiking recurrent neural networks, including those that are meant to be deployed in a neuromorphic system. We propose a selection approach that utilizes a richer understanding of the fitness of an individual network to inform the selection process and to promote diversity in the population. We show that including this feature can provide a significant increase in performance over utilizing a standard selection approach.

Citation Information

Text

author         C. D. Schuman and G. Bruer and A. R. Young and M. Dean and J. S. Plank
title          Understanding Selection and Diversity for Evolution of Spiking Recurrent Neural Networks
booktitle      IJCNN: The International Joint Conference on Neural Networks
month          July
year           2018
address        Rio de Janeiro, Brazil

Bibtex

@INPROCEEDINGS{cby:18:usd,
    author = "C. D. Schuman and G. Bruer and A. R. Young and M. Dean and J. S. Plank",
    title = "Understanding Selection and Diversity for Evolution of Spiking Recurrent Neural Networks",
    booktitle = "IJCNN: The International Joint Conference on Neural Networks",
    month = "July",
    year = "2018",
    address = "Rio de Janeiro, Brazil"
}