Modified Kalman filter based method for training state-recurrent multilayer perceptrons.

Deniz Erdogmus Justin C. Sanchez José C. Príncipe

Published in: NNSP (2002)

Keyphrases

decision making
dynamic programming
training samples
neural network
probabilistic model
multilayer perceptron
bp neural network
training process
filtering algorithm
feedforward neural networks
backpropagation algorithm