Abstract
We are interested in the optimization of the recurrent connection structure of Echo State Networks (ESNs), because their topology can strongly influence performance. We study ESN predictive capacity by numerical simulations on Mackey-Glass time series, and find that a particular small subset of ESNs is much better than ordinary ESNs provided that the topology of the recurrent feedback connections satisfies certain conditions. We argue that the small subset separates two large sets of ESNs and this separation can be characterized in terms of phase transitions. With regard to the criticality of this phase transition, we introduce the notion of Critical Echo State Networks (CESN). We discuss why CESNs perform better than other ESNs.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Jaeger, H.: The Echo State Approach to Analysing and Training Recurrent Neural Networks. Technical Report 148, Fraunhofer Institute for Autonomous Intelligent Systems (2001)
Maas, W., Natschläger, T., Markram, H.: Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations. Neural Computation 14, 2531–2560 (2002)
Jaeger, H.: Short Term Memory in Echo State Networks. Technical report, German National Research Center for Information Technology (2002)
Jaeger, H., Haas, H.: Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication. Science 304, 78–80 (2004)
Ishii, K., Zant, T., Becanovic, V., Plöger, P.: Identification of Motion with Echo State Network. In: Proc. Oceans, pp. 1205–1230 (2004)
Baier, N., De Feo, O.: Chaotic Model Identification Using a Biologically Inspired Algorithm. Aperest, Universidad Complutense de Madrid (2004)
Mayer, N., Browne, M.: Echo State Networks and Self-Prediction. In: Lecture Notes in Computer Science. Volume 3141., Springer Berlin / Heidelberg (2004) 40
Fette, G., Eggert, J.: Short Term Memory and Pattern Matching with Simple Echo State Networks. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3696, pp. 13–18. Springer, Heidelberg (2005)
Jaeger, H.: Reservoir Riddles: Suggestions for Echo State Network Research (Extended Abstract). In: Proceedings of International Joint Conference on Neural Networks, Montreal, Canada (2005)
Sornette, D.: Critical Phenomena in Natural Sciences. Springer Series in Synergetics. Springer, Berlin (2003)
Mackey, M., Glass, L.: Oscillation and chaos in physiological control systems. Science 197, 287–289 (1977)
Cvitanovic, P., Artuso, R., Mainieri, R., Tanner, G., Vattay, G., Whelan, N., Wirzba, A.: Chaos: Classical and Quantum. Niels Bohr Institue, Copenhagen, chaosbook.org version 11 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hajnal, M.A., Lőrincz, A. (2006). Critical Echo State Networks. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds) Artificial Neural Networks – ICANN 2006. ICANN 2006. Lecture Notes in Computer Science, vol 4131. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11840817_69
Download citation
DOI: https://doi.org/10.1007/11840817_69
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-38625-4
Online ISBN: 978-3-540-38627-8
eBook Packages: Computer ScienceComputer Science (R0)