A self-adaptive hardware with resistive switching synapses for experience-based neurocomputing

S. Bianchi, I. Muñoz-Martin, E. Covi, A. Bricalli, G. Piccolboni, A. Regev, G. Molas, J. F. Nodin, F. Andrieu and D. Ielmini ()
Additional contact information
S. Bianchi: Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano and IUNET
I. Muñoz-Martin: Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano and IUNET
E. Covi: Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano and IUNET
A. Bricalli: Weebit Nano
G. Piccolboni: Weebit Nano
A. Regev: Weebit Nano
G. Molas: Weebit Nano
J. F. Nodin: Univ. Grenoble Alpes, CEA, Leti, F-38000
F. Andrieu: Univ. Grenoble Alpes, CEA, Leti, F-38000
D. Ielmini: Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano and IUNET

Nature Communications, 2023, vol. 14, issue 1, 1-14

Abstract: Abstract Neurobiological systems continually interact with the surrounding environment to refine their behaviour toward the best possible reward. Achieving such learning by experience is one of the main challenges of artificial intelligence, but currently it is hindered by the lack of hardware capable of plastic adaptation. Here, we propose a bio-inspired recurrent neural network, mastered by a digital system on chip with resistive-switching synaptic arrays of memory devices, which exploits homeostatic Hebbian learning for improved efficiency. All the results are discussed experimentally and theoretically, proposing a conceptual framework for benchmarking the main outcomes in terms of accuracy and resilience. To test the proposed architecture for reinforcement learning tasks, we study the autonomous exploration of continually evolving environments and verify the results for the Mars rover navigation. We also show that, compared to conventional deep learning techniques, our in-memory hardware has the potential to achieve a significant boost in speed and power-saving.

Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.nature.com/articles/s41467-023-37097-5 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:14:y:2023:i:1:d:10.1038_s41467-023-37097-5

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

DOI: 10.1038/s41467-023-37097-5

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 ().