Abstract
An Echo State Network transforms an incoming time series signal into a high-dimensional state space, and, of course, not every dimension may contribute to the solution. We argue that giving low weights via linear regression is not sufficient. Instead irrelevant features should be entirely excluded from directly contributing to the output nodes. We conducted several experiments using two state-of-the-art feature selection algorithms. Results show significant reduction of the generalization error.
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., Maass, W., Principe, J. (eds.): Special Issue Echo State Networks and Liquid State Machines. Neural Networks 20(3), 287–432 (2007)
Lukosevicius, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Computer Science Review 3(3), 127–149 (2009)
Labusch, K., Barth, E., Martinetz, T.: Sparse Coding Neural Gas: Learning of Overcomplete Data Representations. Neurocomputing 72(7-9), 1547–1555 (2009)
Jaeger, H.: The "echo state" approach to analysing and training recurrent neural networks. GMD Report 148, German National Research Center for Information Technology (2001)
Jaeger, H.: Erratum note, http://www.faculty.jacobs-university.de/hjaeger/pubs/EchoStatesTechRepErratum.pdf
Shi, Z., Han, M.: Support vector echo-state machine for chaotic time-series prediction. IEEE Transactions on Neural Networks 18(2), 359–372 (2007)
Guyon, I., Elissee, A.: An introduction to variable and feature selection. Journal of Machine Learning Research 3, 1157–1182 (2003)
Kohavi, R., John, G.: Wrappers for feature subset selection. Artificial Intelligence 97(1-2), 273–324 (1996)
Zhu, Z., Ong, Y.S., Dash, M.: Markov blanket-embedded genetic algorithm for gene selection. Pattern Recognition 40(11), 3236–3248 (2007)
Dutoit, X., Schrauwen, B., Van Campenhout, J., Stroobandt, D., Van Brussel, H., Nuttin, M.: Pruning and regularisation in reservoir computing. Neurocomputing 72, 1534–1546 (2009)
DEGENA project, http://www.sysca-ag.de/degena/index.htm
Kudo, M., Toyama, J., Shimbo, M.: Data, http://kdd.ics.uci.edu
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kobialka, HU., Kayani, U. (2010). Echo State Networks with Sparse Output Connections. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds) Artificial Neural Networks – ICANN 2010. ICANN 2010. Lecture Notes in Computer Science, vol 6352. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15819-3_47
Download citation
DOI: https://doi.org/10.1007/978-3-642-15819-3_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15818-6
Online ISBN: 978-3-642-15819-3
eBook Packages: Computer ScienceComputer Science (R0)