A second order recursive prediction error algorithm for diagonal recurrent neural networks

Author

Wang, Yongji ; Fernholz, Gregor ; Engell, Sebastian

Author_Institution

Dept. of Chem. Eng., Dortmund Univ., Germany

Volume

1

fYear

1998

fDate

1-4 Sep 1998

Firstpage

172

Abstract

A recursive prediction error (RPE) learning algorithm with second order of convergence for diagonal recurrent neural networks (DRNN) is presented. A guideline for the choice of optimal learning rate is derived from convergence analysis based on Lyapunov theory. With application of this method to model a batch distillation column, the results show that the RPE based DRNN has higher modeling precision and requires a shorter computation time compared to backpropagation (BP) based training of multilayer perceptron nets (MLP)

Keywords

Lyapunov methods; convergence; distillation; learning (artificial intelligence); recurrent neural nets; Lyapunov theory; batch distillation column; convergence analysis; diagonal recurrent neural networks; learning algorithm; optimal learning rate; second order recursive prediction error algorithm; Acceleration; Backpropagation; Chemical engineering; Convergence; Distillation equipment; Multilayer perceptrons; Neural networks; Neurons; Prediction algorithms; Recurrent neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Applications, 1998. Proceedings of the 1998 IEEE International Conference on

Conference_Location

Trieste

Print_ISBN

0-7803-4104-X

Type

conf

DOI

10.1109/CCA.1998.728319

Filename

728319