Evolving unipolar memristor spiking neural networks

Howard, G. D., Bull, L. and de Lacy Costello, B. (2015) Evolving unipolar memristor spiking neural networks. Connection Science, 27 (4). pp. 397-416. ISSN 0954-0091 Available from: http://eprints.uwe.ac.uk/26614

PDF - Accepted Version
Available under License All Rights Reserved.


Publisher's URL: http://dx.doi.org/10.1080/09540091.2015.1080225


Neuromorphic computing - brainlike computing in hardware - typically requires myriad CMOS spiking neurons interconnected by a dense mesh of nanoscale plastic synapses. Memristors are frequently cited as strong synapse candidates due to their statefulness and potential for low-power implementations. To date, plentiful research has focused on the bipolar memristor synapse, which is capable of incremental weight alterations and can provide adaptive self-organisation under a Hebbian learning scheme. In this paper we consider the Unipolar memristor synapse - a device capable of non-Hebbian switching between only two states (conductive and resistive) through application of a suitable input voltage - and discuss its suitability for neuromorphic systems. A self-adaptive evolutionary process is used to autonomously find highly fit network configurations. Experimentation on a two robotics tasks shows that unipolar memristor networks evolve task-solving controllers faster than both bipolar memristor networks and networks containing constant nonplastic connections whilst performing at least comparably.

Item Type:Article
Uncontrolled Keywords:evolution
Faculty/Department:Faculty of Environment and Technology > Department of Computer Science and Creative Technologies
ID Code:26614
Deposited By: Professor L. Bull
Deposited On:07 Sep 2015 10:16
Last Modified:19 Jan 2018 21:27

Request a change to this item

Total Document Downloads in Past 12 Months

Document Downloads

Total Document Downloads

More statistics for this item...