Investigation and Analysis of Hysteresis in Hopfield and T–Model Neural Networks

Zheng TANG  Okihiko ISHIZUKA  Masakazu SAKAI  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E77-A   No.11   pp.1970-1976
Publication Date: 1994/11/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Neural Networks
Keyword: 
neural networks,  Hopfield model,  T–Model,  hysteresis,  local minima,  optimization,  

Full Text: PDF(536.8KB)>>
Buy this Article




Summary: 
We report on an experimental hysteresis in the Hopfield networks and examine the effect of the hysteresis on some important characteristics of the Hopfield networks. The detail mathematic description of the hysteresis phenomenon in the Hopfield networks is given. It suggests that the hysteresis results from fully–connected interconnection of the Hopfield networks and the hysteresis tends to makes the Hopfield networks difficult to reach the global minimum. This paper presents a T–Model network approach to overcoming the hysteresis phenomenon by employing a half–connected interconnection. As a result, there is no hysteresis phenomenon found in the T–Model networks. Theoretical analysis of the T–Model networks is also given. The hysteresis phenomenon in the Hopfield and the T–Model networks is illustrated through experiments and simulations. The experiments agree with the theoretical analysis very well.