Title :
Selection of convergence coefficient with automata learning rule
Author :
Ezzati, N.O. ; Faez, Karim
Author_Institution :
Dept. of Electr. Eng., Amirkabir Univ. of Technol., Tehran, Iran
Abstract :
In this paper an approach for selection of convergence coefficient in a backpropagation learning rule is presented. This approach uses a stochastic automata learning rule for selection of the best coefficient in each step of the learning phase. This approach is applied to a nonlinear function approximation problem. Simulation results show that it gives faster convergence than the conventional and adaptive learning rate backpropagation rules
Keywords :
backpropagation; convergence; feedforward neural nets; function approximation; multilayer perceptrons; stochastic automata; backpropagation learning rule; convergence coefficient; nonlinear function approximation problem; stochastic automata learning rule; Acceleration; Backpropagation algorithms; Convergence; Function approximation; Learning automata; Network topology; Neural networks; Optimization methods; Paper technology; Stochastic processes;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.614202
