Skip to main content

Research Repository

Advanced Search

Evolving unipolar memristor spiking neural networks

Howard, Gerard David; Bull, Larry; De Lacy Costello, Ben

Evolving unipolar memristor spiking neural networks Thumbnail


Gerard David Howard

Lawrence Bull
School Director (Research & Enterprise) and Professor


© 2015 Taylor & Francis. Neuromorphic computing – brain-like computing in hardware – typically requires myriad complimentary metal oxide semiconductor 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 two robotics tasks shows that unipolar memristor networks evolve task-solving controllers faster than both bipolar memristor networks and networks containing constant non-plastic connections whilst performing at least comparably.


Howard, G. D., Bull, L., & De Lacy Costello, B. (2015). Evolving unipolar memristor spiking neural networks. Connection Science, 27(4), 397-416.

Journal Article Type Article
Acceptance Date Jul 2, 2015
Publication Date Oct 2, 2015
Deposit Date Sep 7, 2015
Publicly Available Date Mar 11, 2016
Journal Connection Science
Print ISSN 0954-0091
Electronic ISSN 1360-0494
Publisher Taylor & Francis
Peer Reviewed Peer Reviewed
Volume 27
Issue 4
Pages 397-416
Keywords evolution
Public URL
Publisher URL


You might also like

Downloadable Citations