Kamimura, R., Kamimura, T., & Shultz, T. R. (2001). Self-organization by information control. Proceedings of the IASTED International Symposia, Applied Informatics: Artificial Intelligence and Applications (pp. 188-192). Anaheim, CA: ACTA Press.
In this paper, we propose a new information theoretic self-organization method for artificial neural networks. In our self-organization, we can realize three processes such as competition, cooperation and adaptation in a completely different way from conventional self-organization methods. Competition among neurons can be realized by maximizing information in competitive units, which permits a single winner as well as multiple winners. Cooperation is realized by making neighboring connections behave in the same way. Adaptation is possible by maximizing information content and at the same time by making neighboring connections as similar as possible. We applied the new method to the classification of congressmen according to their voting attitudes. Experimental results confirmed that the congressmen can be spatially distributed, and explicitly classified into two groups by using a single unit as well as a group of units.
Abstracts, papers, chapters, and other documents are posted on this site as an efficient way to distribute reprints. The respective authors and publishers of these works retain all of the copyrights to this material. Anyone copying, downloading, bookmarking, or printing any of these materials agrees to comply with all of the copyright terms. Other than having an electronic or printed copy for fair personal use, none of these works may be reposted, reprinted, or redistributed without the explicit permission of the relevant copyright holders.
To obtain a PDF reprint of this particular article, signal your agreement with these copyright terms by clicking on the statement below.