Deep physical neural networks trained with backpropagation

Logan G. Wright (), Tatsuhiro Onodera (), Martin M. Stein, Tianyu Wang, Darren T. Schachter, Zoey Hu and Peter L. McMahon ()
Additional contact information
Logan G. Wright: Cornell University
Tatsuhiro Onodera: Cornell University
Martin M. Stein: Cornell University
Tianyu Wang: Cornell University
Darren T. Schachter: Cornell University
Zoey Hu: Cornell University
Peter L. McMahon: Cornell University

Nature, 2022, vol. 601, issue 7894, 549-555

Abstract: Abstract Deep-learning models have become pervasive tools in science and engineering. However, their energy requirements now increasingly limit their scalability1. Deep-learning accelerators2–9 aim to perform deep learning energy-efficiently, usually targeting the inference phase and often by exploiting physical substrates beyond conventional electronics. Approaches so far10–22 have been unable to apply the backpropagation algorithm to train unconventional novel hardware in situ. The advantages of backpropagation have made it the de facto training method for large-scale neural networks, so this deficiency constitutes a major impediment. Here we introduce a hybrid in situ–in silico algorithm, called physics-aware training, that applies backpropagation to train controllable physical systems. Just as deep learning realizes computations with deep neural networks made from layers of mathematical functions, our approach allows us to train deep physical neural networks made from layers of controllable physical systems, even when the physical layers lack any mathematical isomorphism to conventional artificial neural network layers. To demonstrate the universality of our approach, we train diverse physical neural networks based on optics, mechanics and electronics to experimentally perform audio and image classification tasks. Physics-aware training combines the scalability of backpropagation with the automatic mitigation of imperfections and noise achievable with in situ algorithms. Physical neural networks have the potential to perform machine learning faster and more energy-efficiently than conventional electronic processors and, more broadly, can endow physical systems with automatically designed physical functionalities, for example, for robotics23–26, materials27–29 and smart sensors30–32.

Date: 2022
References: Add references at CitEc
Citations: View citations in EconPapers (25)

Downloads: (external link)
https://www.nature.com/articles/s41586-021-04223-6 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:nature:v:601:y:2022:i:7894:d:10.1038_s41586-021-04223-6

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

DOI: 10.1038/s41586-021-04223-6

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

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