Evolving spiking networks with variable resistive memories

Howard, Gerard; Bull, Larry; de Lacy Costello, Ben; Gale, Ella; Adamatzky, Andrew

Abstract

Neuromorphic computing is a brainlike information processing paradigm that requires adaptive learning mechanisms. A spiking neuro-evolutionary system is used for this purpose; plastic resistive memories are implemented as synapses in spiking neural networks. The evolutionary design process exploits parameter self-adaptation and allows the topology and synaptic weights to be evolved for each network in an autonomous manner. Variable resistive memories are the focus of this research; each synapse has its own conductance profile which modifies the plastic behaviour of the device and may be altered during evolution. These variable resistive networks are evaluated on a noisy robotic dynamic-reward scenario against two static resistive memories and a system containing standard connections only. The results indicate that the extra behavioural degrees of freedom available to the networks incorporating variable resistive memories enable them to outperform the comparative synapse types. © 2014 by the Massachusetts Institute of Technology.

• Journal Article Type: Letter
• Publication Date: Feb 13, 2014
• Deposit Date: Aug 24, 2015
• Publicly Available Date: Jun 20, 2016
• Journal: Evolutionary Computation
• Print ISSN: 1063-6560
• Electronic ISSN: 1530-9304
• Publisher: Massachusetts Institute of Technology Press (MIT Press)
• Peer Reviewed: Peer Reviewed
• Volume: 22
• Issue: 1
• Pages: 79-103
• DOI: https://doi.org/10.1162/EVCO_a_00103
• Keywords: genetic algorithms, neural networks, hebbian learning, memristors, nonvolatile memory, self-adaptation
• Public URL: https://uwe-repository.worktribe.com/output/824698
• Publisher URL: http://dx.doi.org/10.1162/EVCO_a_00103
• Additional Information: Additional Information : (c) MIT Press 2014. http://www.mitpressjournals.org/toc/evco/22/1
• Contract Date: Jun 20, 2016