HIERtalker: a default hierarchy of high order neural networks that learns to read English aloud

1 January 1988

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

p. 221-228 vol.2
https://doi.org/10.1109/icnn.1988.23932

Abstract

A learning algorithm based on a default hierarchy of high-order neural networks has been developed that is able to generalize as well as handle exceptions. It learns the 'building blocks' or clusters of symbols in a stream that appear repeatedly and that convey certain messages. The default hierarchy prevents a combinatoric generation of rules. A simulator of such hierarchy, HIERtalker, has been applied to the conversion of English words to phonemes. Accuracy is 99% for trained words and ranges from 76% to 96% for sets of new words.

Keywords

This publication has 2 references indexed in Scilit:

Toward memory-based reasoning
Communications of the ACM, 1986
Machine Learning Using a Higher Order Correlation Network
Physica D: Nonlinear Phenomena, 1986