Noise-aware training of neuromorphic dynamic device networks

In materio computing offers the potential for widespread embodied intelligence by leveraging the intrinsic dynamics of complex systems for efficient sensing, processing, and interaction. While individual devices offer basic data processing capabilities, networks of interconnected devices can perform more complex and varied tasks. However, designing such networks for dynamic tasks is challenging in the absence of physical models and accurate characterization of device noise. We introduce the Noise-Aware Dynamic Optimization (NADO) framework for training networks of dynamical devices, using Neural Stochastic Differential Equations (Neural-SDEs) as differentiable digital twins to capture both the dynamics and stochasticity of devices with intrinsic memory. Our approach combines backpropagation through time with cascade learning, enabling effective exploitation of the temporal properties of physical devices. We validate this method on networks of spintronic devices across both temporal classification and regression tasks. By decoupling device model training from network connectivity optimization, our framework reduces data requirements and enables robust, gradient-based programming of dynamical devices without requiring analytical descriptions of their behaviour.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2025-10-16
DOI
https://doi.org/10.1038/s41467-025-64232-1
Citations
1
Primary Topic
Neural Networks and Reservoir Computing
Type
article
Field-Weighted Citation Impact
2.48

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Noise-aware training of neuromorphic dynamic device networks

W. R. Branford, David Ray Griffin, Elisa Donati, Eleni Vasilaki et al.
1 citations
Nature Communications
Neural Networks and Reservoir Computing
2.48
article

Noise-aware training of neuromorphic dynamic device networks

W. R. Branford, David Ray Griffin, Elisa Donati, Eleni Vasilaki, Thomas J. Hayward, Susan Stepney, Jack C. Gartside, Matthew O. A. Ellis, Charles Swindells, Ian T. Vidamour, G. Venkat, Kilian D. Stenning, Luca Manneschi, Chin‐Feng Lai, Dana Hariga, Denis Donskikh, Daanish Sonawala
article en
1 citations

Abstract

In materio computing offers the potential for widespread embodied intelligence by leveraging the intrinsic dynamics of complex systems for efficient sensing, processing, and interaction. While individual devices offer basic data processing capabilities, networks of interconnected devices can perform more complex and varied tasks. However, designing such networks for dynamic tasks is challenging in the absence of physical models and accurate characterization of device noise. We introduce the Noise-Aware Dynamic Optimization (NADO) framework for training networks of dynamical devices, using Neural Stochastic Differential Equations (Neural-SDEs) as differentiable digital twins to capture both the dynamics and stochasticity of devices with intrinsic memory. Our approach combines backpropagation through time with cascade learning, enabling effective exploitation of the temporal properties of physical devices. We validate this method on networks of spintronic devices across both temporal classification and regression tasks. By decoupling device model training from network connectivity optimization, our framework reduces data requirements and enables robust, gradient-based programming of dynamical devices without requiring analytical descriptions of their behaviour.

Nature CommunicationsVol. 16(1)
SIB Swiss Institute of Bioinformatics (CH), Institute for Biomedical Engineering (CH), Imperial College London (GB), University of York (GB), University of Sheffield (GB)
Royal Academy of Engineering, Imperial College London, National Natural Science Foundation of China, Engineering and Physical Sciences Research Council
Openalex Percentile: Top 8%
Neural Networks and Reservoir Computing
2.48
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.