Abstract
Recurrent neural networks are still a challenge in neural investigation. Most commonly used methods have to deal with several problems like local minima, slow convergence or bad learning results because of bifurcations through which the learning system is driven. The following approach, which is inspired by Echo State networks [1], overcomes those problems and enables learning of complex dynamical signals and tasks.
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
Jäger, Herbert, “Output-only learning in recurrent neural networks”, GMD-techreport, Schloss Birlinghoven, Sankt Augustin, Germany, October 14, 2000
Atiya A.F., Parlos A.G., "New results on recurrent neural network training: Unifying the algorithms and accelerating convergence", IEEE Trans. Neural Networks, 11(3): 697–709, 2000
Doya K., "Recurrent neural networks: Supervised learning", The Handbook of Brain Theory and Neural Networks, pages 796–800. MIT Press-Bradford Books, 1995
Sedgewick R.,"Algorithmen in C++", Addison-Wesly, Mnchen, 1992
Rumelhart J.L., "Parallel Distributed Processing: Explorations in the Microstructure of cognition, Volume 1: Foundations", MIT Press, 1986
Fahrhang-Boroujeny B., "Adaptive Filters Theory and Application", National University of Singapore, John Wiley & Sons, Chichester, England, 1998
J. Rubner, K. Schulten, P. Tavan, "A Self-Organizing Network for comlete Feature Extraction", Parallel Processing in Neural Systems and Computers, pages 365–368. Elsevier, Amsterdam, 1990
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fischer, J. (2003). The recurrent IML-network. In: Mira, J., Álvarez, J.R. (eds) Computational Methods in Neural Modeling. IWANN 2003. Lecture Notes in Computer Science, vol 2686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44868-3_39
Download citation
DOI: https://doi.org/10.1007/3-540-44868-3_39
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40210-7
Online ISBN: 978-3-540-44868-6
eBook Packages: Springer Book Archive