Learning chaotic dynamics with neuromorphic network dynamics
Open Access
- 23 October 2025
- journal article
- Published by AIP Publishing in APL Machine Learning
- Vol. 3 (4)
Abstract
This study investigates how dynamical systems may be learned and modeled 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 the 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 maximize 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 optimized for learning complex dynamical systems using only external control parameters.Keywords
All Related Versions
Funding Information
- Australian Research Council (DP220100931)
This publication has 65 references indexed in Scilit:
- Reservoir computing and non-linear dynamics for time series analysis: An application in the financial marketPhysica D: Nonlinear Phenomena, 2025
- Emerging Spatiotemporal Dynamics in Multiterminal Neuromorphic Nanowire Networks Through Conductance Matrices and Voltage MapsAdvanced Electronic Materials, 2024
- Reservoir computing with 3D nanowire networksNeural Networks, 2022
- A systematic exploration of reservoir computing for forecasting complex spatiotemporal dynamicsNeural Networks, 2022
- Prediction of chaotic time series using recurrent neural networks and reservoir computing techniques: A comparative studyMachine Learning with Applications, 2022
- Connectome of memristive nanowire networks through graph theoryNeural Networks, 2022
- Backpropagation algorithms and Reservoir Computing in Recurrent Neural Networks for the forecasting of complex spatiotemporal dynamicsNeural Networks, 2020
- Emergent Criticality in Complex Turing B‐Type Atomic Switch NetworksAdvanced Materials, 2011
- Reservoir computing approaches to recurrent neural network trainingComputer Science Review, 2009
- Advances in Artificial Life2003