DocumentCode
274180
Title
Structured neural networks for Markovian processes
Author
Dodd, N. ; McCulloch, N.
Author_Institution
R. Signals & Radar Establ., Malvern, UK
fYear
1989
fDate
16-18 Oct 1989
Firstpage
319
Lastpage
323
Abstract
A multi-layer perceptron (MLP) containing fixed structured regions consisting of delay lines and feedback units is stable under error-backpropagation. It is proposed that learning with a structured network succeeds where a fully connected, layered network fails. An example is presented: the input to the network is a time varying signal; when a hidden Markov model is used as input, the network learns to output the hidden state probability; performance reaches the theoretical (Baum-Welch forward pass) limit
Keywords
Markov processes; neural nets; Markovian processes; delay lines; error-backpropagation; feedback units; hidden Markov model; learning; multilayer perceptron; neural networks; state probability; structured network; time varying signal;
fLanguage
English
Publisher
iet
Conference_Titel
Artificial Neural Networks, 1989., First IEE International Conference on (Conf. Publ. No. 313)
Conference_Location
London
Type
conf
Filename
51984
Link To Document