Physical deep learning with biologically inspired training method: gradient-free approach for physical hardware

Mitsumasa Nakajima (), Katsuma Inoue (), Kenji Tanaka, Yasuo Kuniyoshi, Toshikazu Hashimoto and Kohei Nakajima ()
Additional contact information
Mitsumasa Nakajima: NTT Device Technology Labs.
Katsuma Inoue: The University of Tokyo
Kenji Tanaka: NTT Device Technology Labs.
Yasuo Kuniyoshi: The University of Tokyo
Toshikazu Hashimoto: NTT Device Technology Labs.
Kohei Nakajima: The University of Tokyo

Nature Communications, 2022, vol. 13, issue 1, 1-12

Abstract: Abstract Ever-growing demand for artificial intelligence has motivated research on unconventional computation based on physical devices. While such computation devices mimic brain-inspired analog information processing, the learning procedures still rely on methods optimized for digital processing such as backpropagation, which is not suitable for physical implementation. Here, we present physical deep learning by extending a biologically inspired training algorithm called direct feedback alignment. Unlike the original algorithm, the proposed method is based on random projection with alternative nonlinear activation. Thus, we can train a physical neural network without knowledge about the physical system and its gradient. In addition, we can emulate the computation for this training on scalable physical hardware. We demonstrate the proof-of-concept using an optoelectronic recurrent neural network called deep reservoir computer. We confirmed the potential for accelerated computation with competitive performance on benchmarks. Our results provide practical solutions for the training and acceleration of neuromorphic computation.

Date: 2022
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/s41467-022-35216-2 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:13:y:2022:i:1:d:10.1038_s41467-022-35216-2

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

DOI: 10.1038/s41467-022-35216-2

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 ().