Pattern grouping strategy makes BP algorithm less sensitive to learning rate.

Yingyang Lu Shenchu Xu Boxi Wu Zhenxiang Chen

Published in: IJCNN (1999)

Keyphrases

learning rate
bp algorithm
error function
convergence rate
learning algorithm
convergence speed
hidden layer
training algorithm
activation function
rapid convergence
weight vector
weight update
bp network
control system
adaptive learning rate
regression model
neural network
fuzzy neural network
feature selection