Title :
An automated approach for selecting the learning rate and momentum in backpropagation networks
Author :
Zaghw, A. ; Dong, W.M.
Author_Institution :
Dept. of Structural Eng., Cairo Univ., Giza, Egypt
fDate :
27 Jun-2 Jul 1994
Abstract :
This paper describes how the backpropagation neural network (BP) can be modified to employ the conjugate gradient method (CG) for speeding up the training process. The application of the conjugate gradient method in this paper was achieved by the appropriate selection of each of the learning rate and momentum in a regular backpropagation program
Keywords :
backpropagation; conjugate gradient methods; neural nets; backpropagation networks; conjugate gradient method; learning rate; momentum; training process; Backpropagation; Character generation; Civil engineering; Equations; Gradient methods; Intelligent networks; Neural networks; Structural engineering; Supervised learning;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374207
