BPS: a learning algorithm for capturing the dynamic nature of speech

1 January 1989

conference paper
Published by Institute of Electrical and Electronics Engineers (IEEE)

p. 417-423 vol.2
https://doi.org/10.1109/ijcnn.1989.118276

Abstract

A novel backpropagation learning algorithm for a particular class of dynamic neural networks in which some units have a local feedback is proposed. Hence these networks can be trained to respond to sequences of input patterns. This algorithm has the same order of space and time requirements as backpropagation applied to feedforward networks. The authors present experimental results and comparisons with a speech recognition problem.

Keywords

This publication has 4 references indexed in Scilit:

Modular Construction of Time-Delay Neural Networks for Speech Recognition
Neural Computation, 1989
Generalization of back-propagation to recurrent neural networks
Physical Review Letters, 1987
Learning sets of filters using back-propagation
Computer Speech & Language, 1987
A Learning Algorithm for Boltzmann Machines*
Cognitive Science, 1985