Evolving unipolar memristor spiking neural networks |
| |
Authors: | David Howard Larry Bull Ben De Lacy Costello |
| |
Affiliation: | 1. QCAT, 1 Technology Court, Pullenvale, Brisbane, QLD 4069, Australia;2. Computer Science and Creative Technologies, University of the West of England, Frenchay Campus, Coldharbour Lane, Bristol BS16 1QY, UK;3. Computer Science and Creative Technologies, University of the West of England, Frenchay Campus, Coldharbour Lane, Bristol BS16 1QY, UK |
| |
Abstract: | 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. |
| |
Keywords: | memristors switching networks plasticity evolution genetic algorithm |
|
|