论文信息 - Bilinear recurrent neural network

Bilinear recurrent neural network

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.<<ETX>>

Dong-Chul Park | Yan Zhu | Yan-Hai Zhu | Dong-Chul Park

[1] Stephen Coombes,et al. Learning higher order correlations , 1993, Neural Networks.

[2] Kwang Y. Lee,et al. Nonlinear system identification using diagonal recurrent neural networks , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[3] A. Lapedes,et al. Nonlinear signal processing using neural networks: Prediction and system modelling , 1987 .

[4] Somnath Mukhopadhyay,et al. A polynomial time algorithm for the construction and training of a class of multilayer perceptrons , 1993, Neural Networks.

[5] James B. Elsner,et al. Predicting time series using a neural network as a method of distinguishing chaos from noise , 1992 .

[6] Kishan G. Mehrotra,et al. Forecasting the behavior of multivariate time series using neural networks , 1992, Neural Networks.

[7] V. J. O H N M A T H. Adaptive Polynomial Filters , 2022 .

[8] Joydeep Ghosh,et al. The pi-sigma network: an efficient higher-order neural network for pattern classification and function approximation , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.