For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Limit Cycles of One-Dimensional Neural Networks with the Cyclic Connection Matrix
Cheol-Young PARK Yoshihiro HAYAKAWA Koji NAKAJIMA Yasuji SAWADA
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1996/06/25
Print ISSN: 0916-8508
Type of Manuscript: Special Section PAPER (Special Section of Papers Selected from 1995 Joint Technical Conference on Circuits/Systems, Computers and Communications (JTC-CSCC '95))
neural networks, continuous-time model, dynamics, limit cycles, equilibrium point,
Full Text: PDF>>
In this paper, a simple method to investigate the dynamics of continuous-time neural networks based on the force (kinetic vector) derived from the equation of motion for neural networks instead of the energy function of the system has been described. The number of equilibrium points and limit cycles of one-dimensional neural networks with the asymmetric cyclic connection matrix has been investigated experimently by this method. Some types of equilibrium points and limit cycles have been theoretically analyzed. The relations between the properties of limit cycles and the number of connections also have been discussed.