Authors:	K.T Vandoorne, W. Dierckx, B. Schrauwen, D. Verstraeten, P. Bienstman, R. Baets, J. Van Campenhout
Title:	Photonic reservoir computing with coupled semiconductor optical amplifiers
Format:	International Conference Proceedings
Publication date:	8/2008
Journal/Conference/Book:	First International Workshop on Optical Supercomputing (OSC 2008), LNCS 5172
Editor/Publisher:	S. Dolev, T. Haist, and M. Oltean, Springer-Verlag Berlin Heidelberg,
Volume(Issue):	p.46-55
Location:	Vienna, Austria
DOI:	10.1007/978-3-540-85673-3_4
Citations:	Look up on Google Scholar
Download:	(6.4MB)

Abstract

We propose photonic reservoir computing as a new approach to optical signal processing and it can be used to handle for example large scale pattern recognition. Reservoir computing is a new learning method from the field of machine learning. This has already led to impressive results in software but integrated photonics with its large bandwidth and
fast nonlinear effects would be a high-performance hardware platform. Therefore we developed a simulation model which employs a network of coupled Semiconductor Optical Amplifiers (SOA) as a reservoir. We show that this kind of photonic reservoir performs even better than classical reservoirs on a benchmark classification task.

Related Research Topics

• Photonic Reservoir Computing