Accession Number : ADA292818

Title :   Stochastic Learning Dynamics and Non-Linear Dimension Reduction.

Descriptive Note : Final rept. 1 Apr 93-31 Mar 94,

Corporate Author : OREGON GRADUATE INST BEAVERTON

Personal Author(s) : Leen, Todd K.

PDF Url : ADA292818

Report Date : 31 MAR 1994

Pagination or Media Count : 20

Abstract : This reports cover research activity under the grant in place from April 1993 through March 1994. Our research addressed algorithms and theory for stochastic learning, non-linear extensions of principal component analysis (PCA) for dimension-reduction, network pruning and methods to incorporate desired invariances into learning. (AN)

Descriptors :   *ALGORITHMS, *STOCHASTIC PROCESSES, *LEARNING MACHINES, *NONLINEAR SYSTEMS, MATHEMATICAL MODELS, IMAGE PROCESSING, NEURAL NETS, OPTIMIZATION, DATA MANAGEMENT, DISTRIBUTED DATA PROCESSING, APPROXIMATION(MATHEMATICS), CONVERGENCE, PATTERN RECOGNITION, PERTURBATIONS, DYNAMIC PROGRAMMING.

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE