Inversion of feedforward neural networks: algorithms and applications

Author

Jensen, Craig A. ; Reed, Russell D. ; Marks, Robert J., II ; El-Sharkawi, Mohamed A. ; Jung, Jae-Byung ; Miyamoto, Robert T. ; Anderson, Gregory M. ; Eggen, C.J.

Author_Institution

Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA

Volume

87

Issue

9

fYear

1999

fDate

9/1/1999 12:00:00 AM

Firstpage

1536

Lastpage

1549

Abstract

There are many methods for performing neural network inversion. Multi-element evolutionary inversion procedures are capable of finding numerous inversion points simultaneously. Constrained neural network inversion requires that the inversion solution belong to one or more specified constraint sets. In many cases, iterating between the neural network inversion solution and the constraint set can successfully solve constrained inversion problems. This paper surveys existing methodologies for neural network inversion, which is illustrated by its use as a tool in query-based learning, sonar performance analysis, power system security assessment, control, and generation of codebook vectors

Keywords

feedforward neural nets; genetic algorithms; inverse problems; learning (artificial intelligence); multilayer perceptrons; power system security; sonar; codebook vectors; constrained inversion; evolutionary algorithms; feedforward neural networks; multilayer perceptron; power system security assessment; query-based learning; sonar; Control systems; Feedforward neural networks; Multi-layer neural network; Neural networks; Neurons; Performance analysis; Power generation; Power system security; Sonar; Training data;

fLanguage

English

Journal_Title

Proceedings of the IEEE

Publisher

ieee

ISSN

0018-9219

Type

jour

DOI

10.1109/5.784232

Filename

784232