Accession Number : ADA285382
Title : Multilayer Piecewise Linear Networks.
Descriptive Note : Final rept. 1993-1994,
Corporate Author : NAVAL AIR WARFARE CENTER WEAPONS DIV CHINA LAKE CA
Personal Author(s) : Alltop, W. O.
Report Date : SEP 1994
Pagination or Media Count : 57
Abstract : Feed-forward layered networks are the simplest neural computers. These networks provide fast compact devices for computing discriminant functions and other mappings applicable to pattern recognition problems. This report treats the problem of weight initialization'/assignment for feed-forward networks with piecewise linear neuron transfer function. Specific transformations are shown to be impossible with a single hidden layer. Techniques are presented for constructing such transformations with two hidden layers. Neural networks, Pattern recognition, Geometry
Descriptors : *NEURAL NETS, *PATTERN RECOGNITION, ALGEBRA, ALLOCATIONS, COMPUTERS, FUNCTIONS, GEOMETRY, DISCRIMINATE ANALYSIS, LAYERS, NETWORKS, WEIGHTING FUNCTIONS, TRANSFER FUNCTIONS, TRANSFORMATIONS.
Subject Categories : Bionics
Distribution Statement : APPROVED FOR PUBLIC RELEASE