Evolving spiking networks with variable resistive memories

Howard, G. D., Bull, L., de Lacy Costello, B. and Adamatzky, A. (2014) Evolving spiking networks with variable resistive memories. Evolutionary Computation, 22 (1). pp. 79-103. ISSN 1063-6560 Available from: http://eprints.uwe.ac.uk/26409

PDF - Published Version

Publisher's URL: http://dx.doi.org/10.1162/EVCO_a_00103


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. 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.

Item Type:Article
Additional Information:(c) MIT Press 2014. http://www.mitpressjournals.org/toc/evco/22/1
Uncontrolled Keywords:evolution, memristor, neural network
Faculty/Department:Faculty of Environment and Technology > Department of Computer Science and Creative Technologies
ID Code:26409
Deposited By: Professor L. Bull
Deposited On:24 Aug 2015 14:06
Last Modified:17 Jan 2018 17:50

Request a change to this item

Total Document Downloads in Past 12 Months

Document Downloads

Total Document Downloads

More statistics for this item...