Optoelectronic Reservoir Computing
Top Cited Papers
Open Access
- 27 February 2012
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 2 (1) , 287
- https://doi.org/10.1038/srep00287
Abstract
Reservoir computing is a recently introduced, highly efficient bio-inspired approach for processing time dependent data. The basic scheme of reservoir computing consists of a non linear recurrent dynamical system coupled to a single input layer and a single output layer. Within these constraints many implementations are possible. Here we report an optoelectronic implementation of reservoir computing based on a recently proposed architecture consisting of a single non linear node and a delay line. Our implementation is sufficiently fast for real time information processing. We illustrate its performance on tasks of practical importance such as nonlinear channel equalization and speech recognition, and obtain results comparable to state of the art digital implementations.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Information processing using a single dynamical node as complex systemNature Communications, 2011
- Why future supercomputing requires opticsNature Photonics, 2010
- Routes to chaos and multiple time scale dynamics in broadband bandpass nonlinear delay electro-optic oscillatorsPhysical Review E, 2009
- Optimization and applications of echo state networks with leaky- integrator neuronsNeural Networks, 2007
- An experimental unification of reservoir computing methodsNeural Networks, 2007
- Chaotic Breathers in Delayed Electro-Optical SystemsPhysical Review Letters, 2005
- From Flow to Map in an Experimental High-Dimensional Electro-Optic Nonlinear Delay OscillatorPhysical Review Letters, 2005
- Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless CommunicationScience, 2004
- Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on PerturbationsNeural Computation, 2002
- New results on recurrent network training: unifying the algorithms and accelerating convergenceIEEE Transactions on Neural Networks, 2000