Towards evolving spiking networks with memristive synapses

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

Abstract

This paper presents a spiking neuro-evolutionary system which implements memristors as neuromodulatory connections, ie whose weights can vary during a trial. The evolutionary design process exploits parameter self-adaptation and a constructionist approach, allowing the number of neurons, connection weights, and inter-neural connectivity pattern to be evolved for each network. We demonstrate that this approach allows the evolution of networks of appropriate complexity to emerge whilst exploiting the ...

• Presentation Conference Type: Conference Paper (unpublished)
• Conference Name: IEEE Symposium on Artificial Life (ALIFE), 2011
• Start Date: Apr 11, 2011
• End Date: Apr 14, 2011
• Publication Date: Jan 1, 2011
• Peer Reviewed: Peer Reviewed
• Pages: 14-21
• Keywords: evolving spiking networks, memristive synapses, Hebbian theory, robot sensing systems, neurons, topology, mathematical model, genetic algorithms
• Public URL: https://uwe-repository.worktribe.com/output/969106
• Publisher URL: http://www.ieee.org/index.html
• Additional Information: Title of Conference or Conference Proceedings : IEEE Symopium on Artificial Life (ALIFE) 2011