Edinburgh Research Explorer

Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication

Research output: Contribution to journalArticle

Related Edinburgh Organisations

Original languageUndefined/Unknown
Pages (from-to)78-80
Number of pages3
JournalScience
Volume304
Issue number5667
DOIs
Publication statusPublished - 1 Apr 2004

Abstract

We present a method for learning nonlinear systems, echo state networks (ESNs). ESNs employ artificial recurrent neural networks in a way that has recently been proposed independently as a learning mechanism in biological brains. The learning method is computationally efficient and easy to use. On a benchmark task of predicting a chaotic time series, accuracy is improved by a factor of 2400 over previous techniques. The potential for engineering applications is illustrated by equalizing a communication channel, where the signal error rate is improved by two orders of magnitude.

ID: 1848964