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.
An Algorithm for Finding All Solutions of a Hysteresis Neural Network
Yuji KOBAYASHI Kenya JIN'NO Toshimichi SAITO
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1999/01/25
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Numerical Analysis and Optimization
finding all solutions, sign test, linear programming, neural network, associative memory, hysteresis,
Full Text: PDF(241.2KB)>>
We consider an algorithm for finding all solutions in order to clarify all the stable equilibrium points of a hysteresis neural network. The algorithm includes sign test, linear programming test and a novel subroutine that divides the solution domain efficiently. Using the hysteresis network, we synthesize an associative memory whose cross connection parameters are trinalized. Applying the algorithm to the case where 10 desired memories are stored into 77 cells network, we have clarified all the solutions. Especially, we have confirmed that no spurious memory exists as the trinalization is suitable.