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

Kilian D. Stenning (), Jack C. Gartside, Luca Manneschi, Christopher T. S. Cheung, Tony Chen, Alex Vanstone, Jake Love, Holly Holder, Francesco Caravelli, Hidekazu Kurebayashi, Karin Everschor-Sitte, Eleni Vasilaki and Will R. Branford
Additional contact information
Kilian D. Stenning: Imperial College London
Jack C. Gartside: Imperial College London
Luca Manneschi: University of Sheffield
Christopher T. S. Cheung: Imperial College London
Tony Chen: Imperial College London
Alex Vanstone: Imperial College London
Jake Love: University of Duisburg-Essen
Holly Holder: Imperial College London
Francesco Caravelli: Los Alamos National Laboratory
Hidekazu Kurebayashi: University College London
Karin Everschor-Sitte: University of Duisburg-Essen
Eleni Vasilaki: University of Sheffield
Will R. Branford: Imperial College London

Nature Communications, 2024, vol. 15, issue 1, 1-15

Abstract: 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.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-024-50633-1 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-50633-1

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-024-50633-1

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().