Share Email Print

Proceedings Paper

Optical signal processing with a network of semiconductor optical amplifiers in the context of photonic reservoir computing
Author(s): Kristof Vandoorne; Martin Fiers; David Verstraeten; Benjamin Schrauwen; Joni Dambre; Peter Bienstman
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Photonic reservoir computing is a hardware implementation of the concept of reservoir computing which comes from the field of machine learning and artificial neural networks. This concept is very useful for solving all kinds of classification and recognition problems. Examples are time series prediction, speech and image recognition. Reservoir computing often competes with the state-of-the-art. Dedicated photonic hardware would offer advantages in speed and power consumption. We show that a network of coupled semiconductor optical amplifiers can be used as a reservoir by using it on a benchmark isolated words recognition task. The results are comparable to existing software implementations and fabrication tolerances can actually improve the robustness.

Paper Details

Date Published: 17 January 2011
PDF: 7 pages
Proc. SPIE 7942, Optoelectronic Integrated Circuits XIII, 79420P (17 January 2011); doi: 10.1117/12.874165
Show Author Affiliations
Kristof Vandoorne, Univ. Gent (Belgium)
Martin Fiers, Univ. Gent (Belgium)
David Verstraeten, Univ. Gent (Belgium)
Benjamin Schrauwen, Univ. Gent (Belgium)
Joni Dambre, Univ. Gent (Belgium)
Peter Bienstman, Univ. Gent (Belgium)

Published in SPIE Proceedings Vol. 7942:
Optoelectronic Integrated Circuits XIII
Louay A. Eldada; El-Hang Lee, 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?