DocumentCode :
2805931
Title :
Convergence of BP Algorithm with Variable Learning Rates for FNN Training
Author :
Shao, Hongmei ; Wu, Wei
Author_Institution :
Dalian University of Technology, China
fYear :
2006
fDate :
Nov. 2006
Firstpage :
245
Lastpage :
252
Abstract :
Convergence results are presented for the batch backpropagation algorithm with variable learning rates for training feedforward neural networks with a hidden layer. The monotonicity of the error function in the training iteration is also proved.
Keywords :
Acceleration; Artificial intelligence; Backpropagation algorithms; Convergence; Error correction; Feedforward neural networks; Genetics; H infinity control; Mathematics; Neural networks;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Artificial Intelligence, 2006. MICAI '06. Fifth Mexican International Conference on
Conference_Location :
Mexico City, Mexico
Print_ISBN :
0-7695-2722-1
Type :
conf
DOI :
10.1109/MICAI.2006.11
Filename :
4022158
Link To Document :
بازگشت