论文信息 - Training Feedforward Neural Networks by Pruning Algorithm Based on Grey Incidence Analysis

Training Feedforward Neural Networks by Pruning Algorithm Based on Grey Incidence Analysis

In this paper, a new pruning algorithm based on grey incidence analysis for feedforward neural networks is presented.The pruned network has the optimal topology with avoiding over training and obtaining good generalization.The removed connections and the incorporated connections are chosen according to the degree of grey incidence of each output sequence of the network units. The simulation results show the effectiveness over several test problems.

Li Wang | Yan Xiong | Dawei Li

[1] R.J.F. Dow,et al. Neural net pruning-why and how , 1988, IEEE 1988 International Conference on Neural Networks.

[2] Giovanna Castellano,et al. An iterative pruning algorithm for feedforward neural networks , 1997, IEEE Trans. Neural Networks.

[3] Deng Ju-Long,et al. Control problems of grey systems , 1982 .

[4] Ehud D. Karnin,et al. A simple procedure for pruning back-propagation trained neural networks , 1990, IEEE Trans. Neural Networks.

[5] Zhao Linming. A Self-configuring Neural Networks based on Grey Connected Analysis and Its Application in Building Water Turbine Models , 1995 .

[6] M. V. Rossum,et al. In Neural Computation , 2022 .

[7] Tang Wan-mei. The Study of the Optimal Structure of BP Nueral Network , 2005 .

[8] David E. Rumelhart,et al. Generalization by Weight-Elimination with Application to Forecasting , 1990, NIPS.

[9] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .