Title :
A multilayer perception with the adaptive learning factor
Author :
Yibin, Song ; Peijin, Wang
Author_Institution :
Coll. of Comput., Yantai Univ., Shandong, China
Abstract :
According to the mechanism of multilayer perception (MLP), this paper describes a method with variable learning rate factors for the improvement of the backpropagation algorithm. The improved algorithm is applied to the learning of the XOR problem and some classification processes. The simulations show the improved algorithm has good effects on speeding up learning process and bettering its learning convergence and robust performance.
Keywords :
backpropagation; multilayer perceptrons; pattern classification; BP algorithm; XOR problem; adaptive learning factor; backpropagation; multilayer perception; variable learning rate factors; Artificial neural networks; Brain modeling; Computational modeling; Convergence; Educational institutions; Equations; Information processing; Joining processes; Neurons; Robustness;
Conference_Titel :
TENCON '02. Proceedings. 2002 IEEE Region 10 Conference on Computers, Communications, Control and Power Engineering
Print_ISBN :
0-7803-7490-8
DOI :
10.1109/TENCON.2002.1182624
