Share Email Print

Proceedings Paper • Open Access

Time delay reservoir computing with VCSEL
Author(s): Jean Benoit Héroux; Gouhei Tanaka; Toshiyuki Yamane; Naoki Kanazawa; Ryosho Nakane; Hidetoshi Numata; Seiji Takeda; Akira Hirose; Daiju Nakano

Paper Abstract

Neural networks in which the interconnections between the nodes are randomly assigned are promising for the realization of neuromorphic devices in which the resource requirements for training are lower than for a fully deterministic system. Reservoir computing is a class of recurrent network for which the input and internal weights are random and fixed over time, and only the output weights are trained via a linear regression. In this work, we review the recent work on photonic reservoirs and describe our recent results on the implementation of a single node system based on multi-mode optical interconnect technology developed for high channel density and low power data transfer applications. We discuss the potential advantages of this approach for the realization of a photonic cluster of reservoirs.

Paper Details

Date Published: 24 February 2020
PDF: 8 pages
Proc. SPIE 11299, AI and Optical Data Sciences, 1129908 (24 February 2020); doi: 10.1117/12.2544981
Show Author Affiliations
Jean Benoit Héroux, IBM Research - Tokyo (Japan)
Gouhei Tanaka, The Univ. of Tokyo (Japan)
Toshiyuki Yamane, IBM Research - Tokyo (Japan)
Naoki Kanazawa, IBM Research - Tokyo (Japan)
Ryosho Nakane, The Univ. of Tokyo (Japan)
Hidetoshi Numata, IBM Research - Tokyo (Japan)
Seiji Takeda, IBM Research - Tokyo (Japan)
Akira Hirose, The Univ. of Tokyo (Japan)
Daiju Nakano, IBM Research - Tokyo (Japan)

Published in SPIE Proceedings Vol. 11299:
AI and Optical Data Sciences
Bahram Jalali; Ken-ichi Kitayama, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?