On a problem of time-varying learning rate influence on the adaptive system dynamics.

Ivan Tyukin Cees van Leeuwen Danil V. Prokhorov Valery A. Terekhov

Published in: CDC (2002)

Keyphrases

learning rate
convergence rate
learning algorithm
rapid convergence
multilayer neural networks
error function
weight vector
convergence speed
hidden layer
activation function
adaptive learning rate
training algorithm
bp neural network algorithm
convergence theorem
natural gradient
linear programming
state space