Photonic Reservoir Computing with Coupled Semiconductor Optical Amplifiers

Authors:
Kristof Vandoorne;Wouter Dierckx;Benjamin Schrauwen;David Verstraeten;Peter Bienstman;Roel Baets;Jan Campenhout
Affiliations:
Photonics Research Group, Dept. of Information Technology, Ghent University --- IMEC, Gent, Belgium 9000;Photonics Research Group, Dept. of Information Technology, Ghent University --- IMEC, Gent, Belgium 9000;PARIS, Dept. of Electronics and Information Systems, Ghent University, Gent, Belgium 9000;PARIS, Dept. of Electronics and Information Systems, Ghent University, Gent, Belgium 9000;Photonics Research Group, Dept. of Information Technology, Ghent University --- IMEC, Gent, Belgium 9000;Photonics Research Group, Dept. of Information Technology, Ghent University --- IMEC, Gent, Belgium 9000;PARIS, Dept. of Electronics and Information Systems, Ghent University, Gent, Belgium 9000
Venue:
OSC '08 Proceedings of the 1st international workshop on Optical SuperComputing
Year:
2008

Citing 5
Cited 0

Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Real-time computing without stable states: a new framework for neural computation based on perturbations

Neural Computation
2007 Special Issue: An experimental unification of reservoir computing methods

Neural Networks
Isolated word recognition with the Liquid State Machine: a case study

Information Processing Letters - Special issue on applications of spiking neural networks
Online stability of backpropagation-decorrelation recurrent learning

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

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.