Trainable hardware for dynamical computing using error backpropagation through physical media

Michiel Hermans (), Michaël Burm, Thomas Van Vaerenbergh, Joni Dambre and Peter Bienstman
Additional contact information
Michiel Hermans: OPERA photonique, Université Libre de Bruxelles
Michaël Burm: Ghent University
Thomas Van Vaerenbergh: Ghent University
Joni Dambre: Ghent University
Peter Bienstman: Ghent University

Nature Communications, 2015, vol. 6, issue 1, 1-8

Abstract: Abstract Neural networks are currently implemented on digital Von Neumann machines, which do not fully leverage their intrinsic parallelism. We demonstrate how to use a novel class of reconfigurable dynamical systems for analogue information processing, mitigating this problem. Our generic hardware platform for dynamic, analogue computing consists of a reciprocal linear dynamical system with nonlinear feedback. Thanks to reciprocity, a ubiquitous property of many physical phenomena like the propagation of light and sound, the error backpropagation—a crucial step for tuning such systems towards a specific task—can happen in hardware. This can potentially speed up the optimization process significantly, offering important benefits for the scalability of neuro-inspired hardware. In this paper, we show, using one experimentally validated and one conceptual example, that such systems may provide a straightforward mechanism for constructing highly scalable, fully dynamical analogue computers.

Date: 2015
References: Add references at CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.nature.com/articles/ncomms7729 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:6:y:2015:i:1:d:10.1038_ncomms7729

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

DOI: 10.1038/ncomms7729

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 ().