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.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Zheng TANG, Okihiko ISHIZUKA, Masakazu SAKAI, "Investigation and Analysis of Hysteresis in Hopfield and T–Model Neural Networks" in IEICE TRANSACTIONS on Fundamentals,
vol. E77-A, no. 11, pp. 1970-1976, November 1994, doi: .
Abstract: 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.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e77-a_11_1970/_p
Copy
@ARTICLE{e77-a_11_1970,
author={Zheng TANG, Okihiko ISHIZUKA, Masakazu SAKAI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Investigation and Analysis of Hysteresis in Hopfield and T–Model Neural Networks},
year={1994},
volume={E77-A},
number={11},
pages={1970-1976},
abstract={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.},
keywords={},
doi={},
ISSN={},
month={November},}
Copy
TY - JOUR
TI - Investigation and Analysis of Hysteresis in Hopfield and T–Model Neural Networks
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1970
EP - 1976
AU - Zheng TANG
AU - Okihiko ISHIZUKA
AU - Masakazu SAKAI
PY - 1994
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E77-A
IS - 11
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - November 1994
AB - 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.
ER -