Neuromorphic overparameterisation and few-shot learning in multilayer physical neural networks

Abstract

Physical neuromorphic computing, exploiting the complex dynamics of physical systems, has seen rapid advancements in sophistication and performance. Physical reservoir computing, a subset of neuromorphic computing, faces limitations due to its reliance on single systems. This constrains output dimensionality and dynamic range, limiting performance to a narrow range of tasks. Here, we engineer a suite of nanomagnetic array physical reservoirs and interconnect them in parallel and series to create a multilayer neural network architecture. The output of one reservoir is recorded, scaled and virtually fed as input to the next reservoir. This networked approach increases output dimensionality, internal dynamics and computational performance. We demonstrate that a physical neuromorphic system can achieve an overparameterised state, facilitating meta-learning on small training sets and yielding strong performance across a wide range of tasks. Our approach’s efficacy is further demonstrated through few-shot learning, where the system rapidly adapts to new tasks.

Metadata

Item Type:	Article
Authors/Creators:	Stenning, K.D. https://orcid.org/0000-0003-0955-3640 Gartside, J.C. https://orcid.org/0000-0002-7044-7399 Manneschi, L. Cheung, C.T.S. Chen, T. Vanstone, A. https://orcid.org/0000-0003-0554-1781 Love, J. Holder, H. https://orcid.org/0000-0002-2102-3880 Caravelli, F. https://orcid.org/0000-0001-7964-3030 Kurebayashi, H. https://orcid.org/0000-0002-2021-1556 Everschor-Sitte, K. https://orcid.org/0000-0001-8767-6633 Vasilaki, E. https://orcid.org/0000-0003-3705-7070 Branford, W.R. https://orcid.org/0000-0002-4821-4097
Copyright, Publisher and Additional Information:	© The Author(s) 2024. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
Keywords:	Computational science; Condensed-matter physics; Nanoscience and technology
Dates:	Published: 27 August 2024 Published (online): 27 August 2024 Accepted: 17 July 2024
Institution:	The University of Sheffield
Academic Units:	The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield)
Depositing User:	Symplectic Sheffield
Date Deposited:	02 Sep 2024 09:37
Last Modified:	02 Sep 2024 09:37
Published Version:	http://dx.doi.org/10.1038/s41467-024-50633-1
Status:	Published
Publisher:	Springer Science and Business Media LLC
Refereed:	Yes
Identification Number:	10.1038/s41467-024-50633-1
Related URLs:	PubMed URL Dataset Dataset
Open Archives Initiative ID (OAI ID):	oai:eprints.whiterose.ac.uk:216654

CORE (COnnecting REpositories)

Neuromorphic overparameterisation and few-shot learning in multilayer physical neural networks

Abstract

Metadata

Download

Published Version

Export

Statistics

Neuromorphic overparameterisation and few-shot learning in multilayer physical neural networks

Abstract

Metadata

Download

Published Version

Related datasets

Export

Statistics