Note to users. If you're seeing this message, it means that your browser cannot find this page's style/presentation instructions -- or possibly that you are using a browser that does not support current Web standards. Find out more about why this message is appearing, and what you can do to make your experience of our site the best it can be.

Science 2 April 2004:
Vol. 304. no. 5667, pp. 78 - 80
DOI: 10.1126/science.1091277
Prev | Table of Contents | Next

Reports

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

Herbert Jaeger* and Harald Haas

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.

International University Bremen, Bremen D-28759, Germany.

* To whom correspondence should be addressed. E-mail: h.jaeger{at}iu-bremen.de

Read the Full Text


THIS ARTICLE HAS BEEN CITED BY OTHER ARTICLES:
Levels and Types of Action Selection: The Action Selection Soup.
P. Ozturk (2009)
Adaptive Behavior 17, 537-554
   Abstract »    PDF »
Embedding Multiple Trajectories in Simulated Recurrent Neural Networks in a Self-Organizing Manner.
J. K. Liu and D. V. Buonomano (2009)
J. Neurosci. 29, 13172-13181
   Abstract »    Full Text »    PDF »
Semantic learning in autonomously active recurrent neural networks.
C. Gros and G. Kaczor (2009)
Logic Jnl IGPL
   Abstract »    PDF »
Structure optimization of reservoir networks.
B. Roeschies and C. Igel (2009)
Logic Jnl IGPL
   Abstract »    PDF »
Memory traces in dynamical systems.
S. Ganguli, D. Huh, and H. Sompolinsky (2008)
PNAS 105, 18970-18975
   Abstract »    Full Text »    PDF »
Grounded Sensorimotor Interaction Histories in an Information Theoretic Metric Space for Robot Ontogeny.
N. A. Mirza, C. L. Nehaniv, K. Dautenhahn, and R. te Boekhorst (2007)
Adaptive Behavior 15, 167-187
   Abstract »    PDF »
Dynamical Basis of Irregular Spiking in NMDA-Driven Prefrontal Cortex Neurons.
D. Durstewitz and T. Gabriel (2007)
Cereb Cortex 17, 894-908
   Abstract »    Full Text »    PDF »


To Advertise     Find Products

Science. ISSN 0036-8075 (print), 1095-9203 (online)