Accession Number:

ADA235581

Title:

Feature Extraction Using an Unsupervised Neural Network

Descriptive Note:

Technical rept.

Corporate Author:

BROWN UNIV PROVIDENCE RI CENTER FOR NEURAL SCIENCE

Personal Author(s):

• Intrator, Nathan

Report Date:

1991-05-03

Pagination or Media Count:

11.0

Abstract:

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.

Descriptors:

• *NEURAL NETS
• *EXTRACTION
• *FUNCTIONS
• *STATISTICAL ANALYSIS
• *DATA REDUCTION
• PARAMETERS
• PROCESSING
• ORIENTATION(DIRECTION)
• ESTIMATES
• REDUCTION
• COPPER
• NERVE CELLS
• INDEXES
• LOSSES
• EQUATIONS
• PURSUIT COURSES
• SYNAPSE
• MODIFICATION
• NETWORKS
• DECISION MAKING
• OPTIMIZATION
• LEARNING
• PROPAGATION

Subject Categories:

• Statistics and Probability
• Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE