Optoelectronic Reservoir Computing

2011/11/30 by Yvan Paquot, François Duport, Anteo Smerieri +4 · 2 citations
Computer Science · Physics and Astronomy · #cs.ET #cs.LG #cs.NE #nlin.CD #physics.optics

paper · pdf · doi:10.1038/srep00287

published as Scientific Reports 2, Article number: 287, (2012) · Contains main paper and two Supplementary Materials

arxiv created 2011/11/30 · arxiv updated 2012/07/06

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 opto-electronic 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.

Cited by

• Understanding Task Performance of Time-Multiplexed Optical Reservoir Computing via Polynomial Expansion
• Deep photonic reservoir computer for nonlinear equalization of 16-level quadrature amplitude modulation signals

Related

• Optimal nonlinear information processing capacity in delay-based reservoir computers
• High-performance photonic reservoir computer based on a coherently driven passive cavity
• In Situ Optimization of an Optoelectronic Reservoir Computer with Digital Delayed Feedback
• Parallel photonic reservoir computing using frequency multiplexing of neurons
• Efficient Optimisation of Physical Reservoir Computers using only a Delayed Input