DocumentCode :
1375969
Title :
Constructing hysteretic memory in neural networks
Author :
Wei, Jyh-Da ; Sun, Chuen-Tsai
Author_Institution :
Dept. of Comput. & Inf. Sci., Nat. Chiao Tung Univ., Hsinchu, Taiwan
Volume :
30
Issue :
4
fYear :
2000
fDate :
8/1/2000 12:00:00 AM
Firstpage :
601
Lastpage :
609
Abstract :
Hysteresis is a unique type of dynamic, which contains an important property, rate-independent memory. In addition to other memory-related studies such as time delay neural networks, recurrent networks, and reinforcement learning, rate-independent memory deserves further attention owing to its potential applications. In this paper, we attempt to define hysteretic memory (rate independent memory) and examine whether or not it could be modeled in neural networks. Our analysis results demonstrate that other memory-related mechanisms are not hysteresis systems. A novel neural cell, referred to herein as the propulsive neural unit, is then proposed. The proposed cell is based on a notion related the submemory pool, which accumulates the stimulus and ultimately assists neural networks to achieve model hysteresis. In addition to training by backpropagation, a combination of such cells can simulate given hysteresis trajectories
Keywords :
backpropagation; fuzzy systems; learning (artificial intelligence); neural nets; hysteresis trajectories; hysteretic memory; neural cell; neural networks; rate-independent memory; recurrent networks; reinforcement learning; time delay neural networks; Backpropagation; Computer networks; Delay effects; History; Hysteresis; Intelligent networks; Learning; Neural networks; Recurrent neural networks; Sun;
fLanguage :
English
Journal_Title :
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
Publisher :
ieee
ISSN :
1083-4419
Type :
jour
DOI :
10.1109/3477.865179
Filename :
865179
Link To Document :
بازگشت