We propose a new mutually coupled plural Neural Networks (N.N.) modules and its application to associative memories from the view point of noncooperative game theory. First, We propose a new dynamical searching model named Parallel Steepest Descent Method with Braking operators (PSDMB) which searches the Nash Equilibrium (NE) points under [0, 1]-interval or nonnegative constraints. Second, we propose a new mutually coupled plural N.N. modules named Game Neural Networks (GNN) to realize the proposed PSDMB with quadratic objective functions. In Addition, we indicate relations between the PSDMB, the GNN and the Lotka-Volterra equation. Last, for an application of the proposed GNN, we propose two kinds of multi modular associative memories which can associate the combined patterns composed of plural partial patterns: (1) the combined patterns are stored as the NE points and robust for noisy inputs; (2) the circulative sequence of the combined patterns are stored as saddles of a heteroclinic cycle.
|ジャーナル||Proceedings of the IEEE International Conference on Systems, Man and Cybernetics|
|出版ステータス||Published - 1998 12月 1|
|イベント||Proceedings of the 1998 IEEE International Conference on Systems, Man, and Cybernetics. Part 2 (of 5) - San Diego, CA, USA|
継続期間: 1998 10月 11 → 1998 10月 14
ASJC Scopus subject areas