Reconfigurable Stochastic neurons based on tin oxide/MoS2 hetero-memristors for simulated annealing and the Boltzmann machine

Xiaodong Yan; Jiahui Ma; Tong Wu; Aoyang Zhang; Jiangbin Wu; Matthew Chin; Zhihan Zhang; Madan Dubey; Wei Wu; Mike Shuo-Wei Chen; Jing Guo; Han Wang

doi:10.1038/s41467-021-26012-5

Nature Communications (Sep 2021)

Reconfigurable Stochastic neurons based on tin oxide/MoS2 hetero-memristors for simulated annealing and the Boltzmann machine

Xiaodong Yan,
Jiahui Ma,
Tong Wu,
Aoyang Zhang,
Jiangbin Wu,
Matthew Chin,
Zhihan Zhang,
Madan Dubey,
Wei Wu,
Mike Shuo-Wei Chen,
Jing Guo,
Han Wang

Affiliations

Xiaodong Yan: Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California
Jiahui Ma: Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California
Tong Wu: Department of Electrical and Computer Engineering, University of Florida
Aoyang Zhang: Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California
Jiangbin Wu: Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California
Matthew Chin: Sensors and Electron Devices Directorate, U.S. Army Research Laboratory
Zhihan Zhang: School of Electrical and Computer Engineering, Georgia Institute of Technology
Madan Dubey: Sensors and Electron Devices Directorate, U.S. Army Research Laboratory
Wei Wu: Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California
Mike Shuo-Wei Chen: Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California
Jing Guo: Department of Electrical and Computer Engineering, University of Florida
Han Wang: Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California

DOI: https://doi.org/10.1038/s41467-021-26012-5
Journal volume & issue: Vol. 12, no. 1
pp. 1 – 8

Abstract

Read online

Boltzmann Machines offer the potential of more efficient solutions to combinatorial problems compared to von Neumann computing architectures. Here, Yan et al introduce a stochastic memristor with dynamically tunable properties, a vital feature for the efficient implementation of a Boltzmann Machine.

Published in Nature Communications

ISSN: 2041-1723 (Online)
Publisher: Nature Portfolio
Country of publisher: United Kingdom
LCC subjects: Science
Website: https://www.nature.com/ncomms/

About the journal