DocumentCode :
2166804
Title :
Comparisons of four learning algorithms for training the multilayer feedforward neural networks with hard-limiting neurons
Author :
Yu, Xiangui ; Loh, Nan K. ; Jullien, G.A. ; Miller, W.C.
Author_Institution :
Dept. of Electr. Eng., Windsor Univ., Ont., Canada
fYear :
1993
fDate :
14-17 Sep 1993
Firstpage :
477
Abstract :
In this paper, two kinds of learning algorithms that have been developed for training multilayer feedforward neural networks with hard-limiting neurons are reviewed. For the modified backpropagation algorithms, their numerical performances of convergence speed and training efficiency are compared; for the architecture generating methods, the architecture sizes of the neural networks generated are compared and their generalization ability are discussed. For any given application problem, some criteria for selecting a suitable training algorithm are also discussed
Keywords :
backpropagation; convergence; feedforward neural nets; architecture generating methods; architecture sizes; convergence speed; generalization ability; hard-limiting neurons; learning algorithms; modified backpropagation algorithms; multilayer feedforward neural networks; numerical performances; training; training efficiency; Artificial neural networks; Backpropagation algorithms; Convergence of numerical methods; Electronic mail; Feedforward neural networks; Multi-layer neural network; Multilayer perceptrons; Neural networks; Neurons; Robotics and automation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Electrical and Computer Engineering, 1993. Canadian Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-2416-1
Type :
conf
DOI :
10.1109/CCECE.1993.332190
Filename :
332190
Link To Document :
بازگشت