DocumentCode
401624
Title
Research on the problem of neural network convergence
Author
Xiong, Jia-jun ; Zhang, Hui
Author_Institution
Dept. of Comput., AFRA, Wuhan, China
Volume
2
fYear
2003
fDate
2-5 Nov. 2003
Firstpage
1132
Abstract
The greatest difficulty for BP network apply in practice is the low learning speed. In this paper, we analyze particularly the reason for the low speed of BP algorithm, bring forward self-adjust learning BP algorithm and the regulating policy of the hidden lay.
Keywords
backpropagation; convergence; feedforward neural nets; self-adjusting systems; BP network; backpropagation algorithm; forward self-adjust learning algorithm; hidden lay policy; momentum factor; neural network convergence; Algorithm design and analysis; Computer networks; Convergence; Educational institutions; Electronic mail; Error correction; Feedforward systems; Joining processes; Neural networks; Switches;
fLanguage
English
Publisher
ieee
Conference_Titel
Machine Learning and Cybernetics, 2003 International Conference on
Print_ISBN
0-7803-8131-9
Type
conf
DOI
10.1109/ICMLC.2003.1259655
Filename
1259655
Link To Document