Generating Explicit Self-Organizing Maps by Information Maximization
In this paper, we propose a new information theoretic method for self-organizing maps. In realizing competition, neither the winner-all-take algorithm nor lateral inhibition is used. Instead, the new method is based upon mutual information maximization between input patterns and competitive units. Thus, competition processes are flexibly controlled to produce explicit self-organizing maps. We applied our method to a road classification problem. Experimental results confirmed that the new method could produce more explicit self-organizing maps than conventional self-organizing methods.
KeywordsInput Pattern Input Unit Cooperative Process Neighboring Neuron Competition Process
Unable to display preview. Download preview PDF.
- 3.Kaski, S., Nikkila, J., Kohonen, T.: Methods for interpreting a self-organized map in data analysis. In: Proceedings of European Symposium on Artificial Neural Networks, Bruges, Belgium (1998)Google Scholar
- 4.Kamimura, R., Kamimura, T., Takeuchi, H.: Greedy information acquisition algorithm: A new information theoretic approach to dynamic information acquisition in neural networks. Connection Science (2002)Google Scholar
- 5.Gatlin, L.L.: Information Theory and Living Systems. Columbia University Press, Columbia (1972)Google Scholar
- 6.Kohonen, T.: Self-Organization Maps. Springer, Heidelberg (1995)Google Scholar
- 7.Marc, M., Hulle, M.V.: Faithful representations and topographic maps. John Wiley and Sons, Inc, New York (2000)Google Scholar