Title :
An adaptive training algorithm for back-propagation neural networks
Author :
Hsin, Hsi-Chin ; Li, Ching-Chung ; Sun, Mingui ; Sclabassi, Robert J.
Author_Institution :
Dept. of Electr. Eng., Pittsburgh Univ., PA, USA
fDate :
3/1/1995 12:00:00 AM
Abstract :
A dynamic learning rate for back-propagation training of artificial neural networks is proposed as a weighted average of direction cosines of the incremental weight vectors of the current and previous steps. Experiments on training an EEG-based sleep state pattern recognition scheme have demonstrated its improved performance
Keywords :
backpropagation; neural nets; EEG-based sleep state pattern recognition scheme; adaptive training algorithm; back-propagation neural networks; direction cosines weighted average; dynamic learning rate; Approximation algorithms; Artificial neural networks; Convergence; Least squares approximation; Neural networks; Neurons; Pattern recognition; Sleep; Sun; Surgery;
Journal_Title :
Systems, Man and Cybernetics, IEEE Transactions on
