Title :
Parallel training algorithm of BP neural networks
Author :
Jun, Li ; Yuanxiang, Li ; Jingwen, Xu ; Jinbo, Zhang
Author_Institution :
Lab. of Software Eng., Wuhan Univ., China
Abstract :
As the training process of backpropagation neural networks converges slowly and immerses in local vibration frequently, an algorithm named the parallel training algorithm is proposed, which is based on the master/slave model and training learning samples in each search subspace at the same time. The experiment results show that this algorithm converges at high rate and reaches global minimum quickly
Keywords :
backpropagation; convergence; neural nets; parallel algorithms; search problems; backpropagation; convergence; master/slave model; neural networks; parallel learning algorithm; search subspace; Feedforward neural networks; Laboratories; Master-slave; Multi-layer neural network; Neural networks; Software algorithms; Software engineering;
Conference_Titel :
Intelligent Control and Automation, 2000. Proceedings of the 3rd World Congress on
Conference_Location :
Hefei
Print_ISBN :
0-7803-5995-X
DOI :
10.1109/WCICA.2000.863356
