Title :
Analysis of hysteresis in Hopfield neural networks
Author :
Tang, Zheng ; Ishizuka, Okihiko ; Sakai, Masakazu ; Matsumoto, Hiroki
Author_Institution :
Dept. of Electron. Eng., Miyazaki Univ., Japan
Abstract :
We report on an experimental hysteresis in the Hopfield network and give a detail mathematical description of the hysteresis phenomenon. It is the hysteresis that makes the Hopfield network difficult to reach the global minimum. This paper presents a T-Model network approach to overcoming the hysteresis phenomenon. Theoretical analysis of the T-Model network 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 :
Hopfield neural nets; hysteresis; Hopfield neural networks; T-model network; hysteresis; Computer networks; Differential equations; Hopfield neural networks; Hysteresis; Intelligent networks; Matrix converters; Neural networks; Neurons; Symmetric matrices;
Conference_Titel :
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN :
0-7803-1421-2
DOI :
10.1109/IJCNN.1993.716824
