Evolving unipolar memristor spiking neural networks

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

Abstract

© 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.

Citation

Howard, G. D., Bull, L., & De Lacy Costello, B. (2015). Evolving unipolar memristor spiking neural networks. Connection Science, 27(4), 397-416. https://doi.org/10.1080/09540091.2015.1080225

• Journal Article Type: Article
• Acceptance Date: Jul 2, 2015
• Publication Date: Oct 2, 2015
• 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
• DOI: https://doi.org/10.1080/09540091.2015.1080225
• Keywords: evolution
• Public URL: https://uwe-repository.worktribe.com/output/805830
• Publisher URL: http://dx.doi.org/10.1080/09540091.2015.1080225