A dynamic model for neural networks

Author

Dabbous, T.E. ; Shafie, K.A.

Author_Institution

Dept. of Electr. & Comput. Eng., Higher Tech. Inst. Ramadan 10th City, Egypt

fYear

1999

fDate

23-25 Feb 1999

Abstract

We present a novel dynamical model for neural networks. The model consists of two sets of differential equations: one for the hidden layers and the other for the output layer. Since the model parameters (or weights) are assumed unknown, one may choose these parameters so that the neural output behaves in a certain prescribed manner. The proposed model can be very useful for many engineering applications such as communication, control and system identification. Numerical examples are given to show the effectiveness of the proposed neural model

Keywords

control engineering; difference equations; identification; neural nets; nonlinear systems; adaptive control; communication; control; differential equations; dynamic model; engineering applications; hidden layers; image processing; model parameters; neural model; neural networks; neural output; output layer; pattern recognition; system identification; weights; Cities and towns; Communication system control; Control system synthesis; Control theory; Differential equations; Neural networks; Neurons; Nonlinear dynamical systems; Nonlinear filters; Target tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Radio Science Conference, 1999. NRSC '99. Proceedings of the Sixteenth National

Conference_Location

Cairo

Print_ISBN

977-5031-62-1

Type

conf

DOI

10.1109/NRSC.1999.760928

Filename

760928