Bilinear recurrent neural network

Author

Park, Dong C. ; Zhu, Yan

Author_Institution

Dept. of Electr. & Comput. Eng., Florida Int. Univ., Miami, FL, USA

Volume

3

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

1459

Abstract

A recurrent neural network and its training algorithm are proposed in this paper. Since the proposed algorithm is based on the bilinear polynomial, it can model many nonlinear systems with much more parsimony than the higher order neural networks based on Volterra series. The proposed bilinear recurrent neural network (BLRNN) is compared with multilayer perceptron neural networks (MLPNN) for time series prediction problems. The results show that the BLRNN is robust and outperforms the MLPNN in terms of prediction accuracy

Keywords

learning (artificial intelligence); multilayer perceptrons; prediction theory; recurrent neural nets; time series; bilinear polynomial; bilinear recurrent neural network; multilayer perceptron neural networks; nonlinear systems; prediction accuracy; time series prediction problems; training algorithm; Artificial neural networks; Computer networks; Electronic mail; Feedforward neural networks; Intelligent networks; Neural networks; Neurons; Nonlinear systems; Polynomials; Recurrent neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374501

Filename

374501