Evolving Unipolar Memristor Spiking Neural Networks

TL;DR

This paper explores the use of unipolar memristor synapses in spiking neural networks, demonstrating their effectiveness and faster evolution in robotic tasks compared to bipolar memristors and fixed connections.

Contribution

It introduces unipolar memristor synapses for neuromorphic computing and shows their advantages through evolutionary robotics experiments.

Findings

Unipolar memristor networks evolve faster than bipolar memristor networks.

Unipolar memristor networks perform comparably to bipolar networks in task-solving.

Unipolar memristors are suitable for low-power neuromorphic systems.

Abstract

Neuromorphic computing --- brainlike computing in hardware --- typically requires myriad CMOS spiking neurons interconnected by a dense mesh of nanoscale plastic synapses. Memristors are frequently citepd 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.