Summary
International Symposium on Nonlinear Theory and its Applications
2010
Session Number:C3L-C
Session:
Number:C3L-C4
Discrete Higher Order Inverse Function Delayed Network
Takahiro Sota, Yoshihiro Hayakawa, Shigeo Sato, Koji Nakajima,
pp.615-618
Publication Date:2010/9/5
Online ISSN:2188-5079
DOI:10.34385/proc.44.C3L-C4
PDF download (73.9KB)
Summary:
The Inverse function Delayed model (ID model) is a neuron model that has dynamics effected by negative resistance. The negative resistance can destabilize local minimum states that are undesirable network responses. Actually, we have demonstrated that the ID network can perfectly remove all local minima with N-Queen problems or 4-Color problems where stationary states are only correct answers. Meanwhile, about the case of Traveling Salesman Problems or Quadratic Assignment Problems, we also applied the ID network to them with the same method by introducing quartic-form energy function and higher order connections. In this paper, we introduce the discrete ID model with higher order connections to achieve the hardware implementation of the network.