DocumentCode :
3380469
Title :
Two-phases Parallel Neural Network Algorithm Based on RPROP
Author :
Xiong, Zhongyang ; Zhang, Yufang ; Ou, Ling ; Li, Li
Author_Institution :
Dept. of Comput. Sci., Chongqing Univ., Chongqing
fYear :
2005
fDate :
21-24 Nov. 2005
Firstpage :
1
Lastpage :
6
Abstract :
BP algorithm is widely used in the field of business intelligence. Aimed at improving its relatively slow convergence speed and its tendency to be trapped in local minima easily, an improved two-phases parallel algorithm is presented in this paper. The first parallel operation is to cast about for minima area so as to avoid getting into local optimal solution to some extent and accelerate convergence, thereby reducing the number of epochs. The second parallel operation is to shorten learning time. The experiments demonstrate that the improved two-phases parallel BP algorithm has the better performance of speedup.
Keywords :
backpropagation; convergence; neural nets; parallel algorithms; business intelligence; convergence speed; parallel neural network algorithm; resilient backpropagation; Backpropagation algorithms; Business communication; Communications technology; Computer science; Convergence; Feeds; Neural networks; Neurons; Partitioning algorithms; Robust stability; Neural Network; Parallel; RPROP Algorithm; Two-phases;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
TENCON 2005 2005 IEEE Region 10
Conference_Location :
Melbourne, Qld.
Print_ISBN :
0-7803-9311-2
Electronic_ISBN :
0-7803-9312-0
Type :
conf
DOI :
10.1109/TENCON.2005.301307
Filename :
4085107
Link To Document :
بازگشت