Title :
Research on the problem of neural network convergence
Author :
Xiong, Jia-jun ; Zhang, Hui
Author_Institution :
Dept. of Comput., AFRA, Wuhan, China
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;
Conference_Titel :
Machine Learning and Cybernetics, 2003 International Conference on
Print_ISBN :
0-7803-8131-9
DOI :
10.1109/ICMLC.2003.1259655
