Accession Number : AD0670845

Title :   THE INFLUENCE OF NETWORK STRUCTURE ON THE PERFORMANCE OF LEARNING SYSTEMS,

Corporate Author : BELL AEROSPACE CORP BUFFALO N Y

Personal Author(s) : Goerner,Johannes G. ; Gerhardt,Lester A. ; Drake,Kenneth W. ; Cadzow,James A. ; Powell,Frederic D.

Report Date : 31 OCT 1967

Pagination or Media Count : 92

Abstract : The report summarizes research on means for improving the discrimination capability of linear single-gain layer networks. Improvements are considered via (a) nonlinear pre-processors, such as the A/D converter, the quantizer, and other encoders, the generation of functionals of the individual pattern components, and (b) cascading of these networks. All result essentially in introducing a nonlinear decision surface instead of the decision hyperplane as defined by a linear net. Significant improvements are obtainable that widen the application of such networks to practical problems. As an example, the modeling of an air cushion vehicle is discussed. (Author)

Descriptors :   (*LEARNING MACHINES, MATHEMATICAL LOGIC), DECISION THEORY, ADAPTIVE SYSTEMS, PROBABILITY DENSITY FUNCTIONS, CLASSIFICATION, OPTIMIZATION, PATTERN RECOGNITION, GROUND EFFECT MACHINES

Subject Categories : Computer Programming and Software
      Bionics

Distribution Statement : APPROVED FOR PUBLIC RELEASE