Abstract
Adaptive systems research is mainly concentrated around optimizing cost functions suitable to problems. Recently, Principe et al. proposed a particle interaction model for information theoretical learning. In this paper, inspired by this idea, we propose a generalization to the particle interaction model for learning and system adaptation. In addition, for the special case of supervised multi-layer perceptron (MLP) training we propose the interaction force backpropagation algorithm, which is a generalization of the standard error backpropagation algorithm for MLPs.
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
Haykin, S.: Neural Networks: A Comprehensive Foundation. 2nd edn. Prentice Hall, New Jersey (1999)
Oja, E.: Subspace Methods for Pattern Recognition. Wiley, New York (1983)
Haykin, S. (ed.): Unsupervised Adaptive Filtering, Vol. 1: Blind Source Separation. Wiley, New York (2000)
Haykin, S. (ed.): Unsupervised Adaptive Filtering, Vol. 2: Blind Deconvolution. Wiley, New York (2000)
Hyvarinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. Wiley, New York (2001)
Principe, J.C., Xu, D., Fisher, J.W.: Information Theoretic Learning. In: Haykin, S. (ed.): Unsupervised Adaptive Filtering, Vol. 1: Blind Source Separation. Wiley, New York (2000)
Erdogmus, D. Principe, J.C.: Generalized Information Potential Criterion for Adaptive System Training. To appear in IEEE Trans. in Neural Networks (2002)
Santamaria, I., Erdogmus, D., Principe, J.C.: Entropy Minimization for Digital Communications Channel Equalization. To appear in IEEE Trans. on Signal Processing (2002)
Torkkola, K., Campbell, W.M.: Mutual Information in Learning Feature Transformations. In: Proceedings of the International Conference on Machine Learning. Stanford (2000)
Parzen, E.: On Estimation of a Probability Density Function and Mode. In: Time Series Analysis Papers. Holden-Day, California (1967)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Erdogmus, D., Principe, J.C., Vielva, L., Luengo, D. (2002). Potential Energy and Particle Interaction Approach for Learning in Adaptive Systems. In: Dorronsoro, J.R. (eds) Artificial Neural Networks — ICANN 2002. ICANN 2002. Lecture Notes in Computer Science, vol 2415. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46084-5_74
Download citation
DOI: https://doi.org/10.1007/3-540-46084-5_74
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44074-1
Online ISBN: 978-3-540-46084-8
eBook Packages: Springer Book Archive