DocumentCode :
3105353
Title :
Dynamic properties of Elman and modified Elman neural network
Author :
Cheng, Yuan-Chu ; Qi, Wei-Min ; Cai, Wei-you
Author_Institution :
Dept. of Power Eng., Wuhan Univ., China
Volume :
2
fYear :
2002
fDate :
2002
Firstpage :
637
Abstract :
The Elman network is a well-known recurrent neural network. In this paper, an overview of the structure of the Elman neural network and its modified form are presented. Both have trainable feed-forward connections. Then, by comparing with the discrete PID control algorithm, their dynamic characteristics are fully discussed using the z transform function. Finally, we conclude that the modified Elman network has better dynamic properties.
Keywords :
Z transforms; dynamic response; feedforward neural nets; neurocontrollers; recurrent neural nets; three-term control; Elman neural network; discrete PID control algorithm; dynamic characteristics; dynamic properties; modified Elman neural network; overview; recurrent neural network; trainable feed-forward connections; z transform function; Computer aided instruction; Electronic mail; Feedforward neural networks; Feedforward systems; Neural networks; Power engineering; Recurrent neural networks; Speech recognition; System identification; Three-term control;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning and Cybernetics, 2002. Proceedings. 2002 International Conference on
Print_ISBN :
0-7803-7508-4
Type :
conf
DOI :
10.1109/ICMLC.2002.1174413
Filename :
1174413
Link To Document :
بازگشت