Training of the dynamic neural networks via constrained optimisation

Author

Patan, Krzysztof

Author_Institution

Inst. of Control & Comput. Eng., Zielona Gora Univ., Poland

Volume

1

fYear

2004

fDate

25-29 July 2004

Lastpage

200

Abstract

The paper deals with training of a dynamic neural network by using an algorithm which takes into account constraints on network parameters. A neural network considered is composed of dynamic neurons, which contain inner feedbacks. To train this network, a stochastic approximation method is applied. The stability analysis during training is also investigated. As a result of this analysis, a learning algorithm based on a constrained optimization has been elaborated. Efficiency of a proposed approach is presented using an example of modelling of an unknown non-linear dynamic system.

Keywords

feedback; learning (artificial intelligence); neural nets; optimisation; stability; stochastic processes; constrained optimisation; dynamic neural network; dynamic neurons; inner feedbacks; stability analysis; stochastic approximation method; unknown nonlinear dynamic system; Artificial neural networks; Constraint optimization; Delay lines; IIR filters; Neural networks; Neurofeedback; Neurons; Nonlinear dynamical systems; Recurrent neural networks; Stability analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-8359-1

Type

conf

DOI

10.1109/IJCNN.2004.1379897

Filename

1379897