Application of Game Theory to Neuronal Networks.pdfVIP

Hindawi Publishing Corporation Advances in Artificial Intelligence Volume 2010, Article ID 521606, 12 pages doi:10.1155/2010/521606 Research Article Application of Game Theory to Neuronal Networks Alfons Schuster1, 2 and Yoko Yamaguchi2 1 School of Computing and Mathematics, Faculty of Computing and Engineering, University of Ulster, Shore Road, Newtownabbey, Co. Antrim BT37 0QB, Northern Ireland 2 Laboratory for Dynamics of Emergent Intelligence, RIKEN Brain Science Institute, Wako-shi, Saitama 351-0198, Japan Correspondence should be addressed to Alfons Schuster, a.schuster@ulster.ac.uk Received 28 August 2009; Accepted 2 October 2009 Academic Editor: Naoyuki Sato Copyright © 2010 A. Schuster and Y. Yamaguchi. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The paper is a theoretical investigation into the potential application of game theoretic concepts to neural networks (natural and artificial). The paper relies on basic models but the findings are more general in nature and therefore should apply to more complex environments. A major outcome of the paper is a learning algorithm based on game theory for a paired neuron system. 1. Introduction In the remainder of this text, Section 2 summarizes the motivation for this paper and validates an intuitively Individual neurons are the building blocks for more complex appealing (though not unproblematic) relationship between neural circuits. In natural systems these more complex neural