Publication View

Mathematical Theory of Neural Networks (2006)

Abstract
This report provides a summary of the grant work by the principal investigators in the area of neural networks. The topics covered deal with: analysis of networks from the viewpoint of analog computational devices, exploring limitations imposed by resource constraints; questions of parameter identification of recurrent nets; use of feedforward nets for function approximation and interpolation problems; systems theory (observability and other properties) for nets; and the use of neural networks for the control of nonlinear systems.

Publication details
Download http://handle.dtic.mil/100.2/ADA286508
Contributors RUTGERS - THE STATE UNIV NEW BRUNSWICK NJ DEPT OF MATHEMATICS
Repository Defense Technical Information Center OAI-PMH Repository (United States)
Keywords OPERATIONS RESEARCH, CYBERNETICS, *NEURAL NETS, *SYSTEMS ANALYSIS, MATHEMATICAL MODELS, COMPUTATIONS, MATHEMATICAL LOGIC, IDENTIFICATION, LIMITATIONS, FEEDBACK, ARTIFICIAL INTELLIGENCE, CONTROL THEORY, ANALOGS, INTERPOLATION, APPROXIMATION(MATHEMATICS), NONLINEAR SYSTEMS, LEARNING MACHINES, PARAMETERS, ALGORITHMS, PE61102F
Language eng