Abstract
A game-theoretic formulation of adaptive categorization mechanism for ART-type networks is proposed in this paper. We have derived the game-theoretic model Γ AC for competitive processes of categorization of ART-type networks and an update rule for vigilance parameters using the concept of learning automata. Numbers of clusters generated by ART adaptive categorization are similar regardless of the initial vigilance parameters ρ assigned to the ART networks as demonstrated in the experiments provided. The proposed ART adaptive categorization mechanism can thus avoid the problem of choosing suitable vigilance parameter a priori for pattern categorization.
This work is supported in part by the Hong Kong Research Grant Council under grant CUHK 4151/97E
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
G. A. Carpenter and S. Grossberg. A Massively Parallel Architecture for a Self-Organizing Neural Pattern Recognition Machine. Computer Vision, Graphics and Image Processing, 37:54–115 1987.
G. A. Carpenter, S. Grossberg, and D. B. Rosen. Fuzzy ART: Fast Stable Leaming and Categorization of Analog Patterns by an Adaptive Resonance System. Neural Networks, 4:759–71 1991.
N. Vlajic and H. C. Card. Categorizing Web pages using Modified ART. In 1998 IEEE Canadian Conference on Electrical and Computer Engineering, volume 1, pages 313–316, 1998.
W. K. Fung and Y. H. Liu. A Game-theoretic Formulation on Adaptive Categorization in ART Networks. In Proceedings of 1999 International Joint Conference on Neural Networks IJCNN’99, volume 2, pages 1081–1086, 1999.
K. S. Narendra and M. A. L. Thathachar. Learning Automata: An Introduction. Prentice Hall, 1989.
D. Fudenberg and J. Tirole. Game Theory. The MIT Press, 1991.
Jr. J. H. Williams. Fundamentals of Applied Dynamics. John Wiley and Sons, 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fung, Wk., Liu, Yh. (2001). A Game-Theoretic Adaptive Categorization Mechanism for ART-Type Networks. In: Dorffner, G., Bischof, H., Hornik, K. (eds) Artificial Neural Networks — ICANN 2001. ICANN 2001. Lecture Notes in Computer Science, vol 2130. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44668-0_24
Download citation
DOI: https://doi.org/10.1007/3-540-44668-0_24
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42486-4
Online ISBN: 978-3-540-44668-2
eBook Packages: Springer Book Archive