Evolving Spiking Networks with Variable Resistive Memories

TL;DR

This paper introduces a neuro-evolutionary approach to design spiking neural networks with variable resistive memories, enabling adaptive learning and improved performance in noisy robotic tasks.

Contribution

It presents a novel method for evolving spiking neural networks with variable resistive synapses, allowing dynamic conductance profiles and enhanced adaptability.

Findings

Variable resistive memories outperform static ones in noisy environments

Evolved networks with variable resistive synapses show higher adaptability

The approach enables autonomous topology and weight evolution

Abstract

Neuromorphic computing is a brainlike information processing paradigm that requires adaptive learning mechanisms. A spiking neuro-evolutionary system is used for this purpose; plastic resistive memories are implemented as synapses in spiking neural networks. The evolutionary design process exploits parameter self-adaptation and allows the topology and synaptic weights to be evolved for each network in an autonomous manner. Variable resistive memories are the focus of this research; each synapse has its own conductance profile which modifies the plastic behaviour of the device and may be altered during evolution. These variable resistive networks are evaluated on a noisy robotic dynamic-reward scenario against two static resistive memories and a system containing standard connections only. Results indicate that the extra behavioural degrees of freedom available to the networks incorporating variable resistive memories enable them to outperform the comparative synapse types.