Learning Chaotic Dynamics with Neuromorphic Network Dynamics

TL;DR

This paper demonstrates how a memristive neuromorphic network can learn and model chaotic dynamical systems, revealing optimal input configurations for effective prediction and system exploration.

Contribution

It introduces a method to optimize neuromorphic networks based on memristive circuits for learning complex dynamical systems through external input tuning.

Findings

Optimal input voltages maximize memristor dynamic range exploration.

Increasing input coverage suppresses less useful nonlinear responses.

Physical neuromorphic networks can be optimized for complex system learning.

Abstract

This study investigates how dynamical systems may be learned and modelled with a neuromorphic network which is itself a dynamical system. The neuromorphic network used in this study is based on a complex electrical circuit comprised of memristive elements that produce neuro-synaptic nonlinear responses to input electrical signals. To determine how computation may be performed using the physics of the underlying system, the neuromorphic network was simulated and evaluated on autonomous prediction of a multivariate chaotic time series, implemented with a reservoir computing framework. Through manipulating only input electrodes and voltages, optimal nonlinear dynamical responses were found when input voltages maximise the number of memristive components whose internal dynamics explore the entire dynamical range of the memristor model. Increasing the network coverage with the input electrodes was found to suppress other nonlinear responses that are less conducive to learning. These results provide valuable insights into how a physical neuromorphic network device can be feasibly optimised for learning complex dynamical systems using only external control parameters.