Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

January 1992, Vol. 4, No. 1, Pages 98-107
(doi: 10.1162/neco.1992.4.1.98)
© 1992 Massachusetts Institute of Technology
Feature Extraction Using an Unsupervised Neural Network
Article PDF (579.67 KB)
Abstract

A novel unsupervised neural network for dimensionality reduction that seeks directions emphasizing multimodality is presented, and its connection to exploratory projection pursuit methods is discussed. This leads to a new statistical insight into the synaptic modification equations governing learning in Bienenstock, Cooper, and Munro (BCM) neurons (1982). The importance of a dimensionality reduction principle based solely on distinguishing features is demonstrated using a phoneme recognition experiment. The extracted features are compared with features extracted using a backpropagation network.