Accession Number : AD0816224

Title :   NONLINEAR FUNCTION MODELING WITH NEURAL NETS.

Descriptive Note : Annual progress rept. no. 2, 15 Jun 66-14 Jun 67,

Corporate Author : BELL AEROSYSTEMS CO BUFFALO NY

Personal Author(s) : Goerner, Johannes G. ; Powell, Frederic D.

Report Date : 14 JUN 1967

Pagination or Media Count : 31

Abstract : Some of the general properties of linear neural nets are reviewed and their applications to adaptive decorrelation of a set of correlated signals and to adaptive inversion of matrices are outlined. The effects on modeling accuracy using non-linear preprocessing by quantizing the inputs to adaptive nets have been studied. The properties of nonlinear modeling nets with and without linear pole-adaption are discussed and the information and convergence aspects of the several types of modelers are considered. A powerful quantizer for high accuracy modeling is derived. It transmits in separable forms, and without cross-coupling, information specifying the class to which the input belongs and also the value of the input at the instant. This technique affords piecewise-linear approximation of any single-valued nonlinear transformation of the input; it also yields rapid convergence of the adaptive weights and high accuracy of modeling. (Author)

Descriptors :   (*ADAPTIVE SYSTEMS, LINEAR SYSTEMS), NERVOUS SYSTEM, MATHEMATICAL MODELS, INPUT OUTPUT DEVICES, CONVERGENCE, FUNCTIONS(MATHEMATICS), COMPUTERS, MATRICES(MATHEMATICS), ACCURACY, OPTIMIZATION, APPROXIMATION(MATHEMATICS), LEAST SQUARES METHOD, ERRORS, FEEDBACK, MATHEMATICAL ANALYSIS, ALGORITHMS, CORRELATION TECHNIQUES, INFORMATION THEORY, CYBERNETICS.

Subject Categories : Operations Research

Distribution Statement : APPROVED FOR PUBLIC RELEASE