DID YOU KNOW? DTIC has over 3.5 million final reports on DoD funded research, development, test, and evaluation activities available to our registered users. Click HERE
to register or log in.
Feature Extraction Using an Unsupervised Neural Network
BROWN UNIV PROVIDENCE RI CENTER FOR NEURAL SCIENCE
Pagination or Media Count:
A novel unsupervised neural network for dimensionality reduction which seeks directions emphasizing distinguishing features in the data is presented. A statistical framework for the parameter estimation problem associated with this neural network is given and its connection to exploratory projection pursuit methods is established. The network is shown to minimize a loss function projection index over a set of parameters, yielding an optimal decision rule under some norm. A specific projection index that favors directions possessing multimodality is presented. This leads to a similar form to 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 linguistically motivated phoneme recognition experiment, and compared with feature extraction using principal components and back propagation network.
APPROVED FOR PUBLIC RELEASE