论文信息 - The Layered Feed-Forward Neural Networks and Its Rule Extraction

The Layered Feed-Forward Neural Networks and Its Rule Extraction

A mathematical study of the layered feed-forward neural networks is proposed here for identifying the rules suggested in the network. The mathematical study, not a data analysis, is proposed for identifying the premise association with each rule. It, hopefully, can be used further to deal with the predicament of ANN being a black box.

Chih-Chung Lin | Ray Tsaih

[1] Kazumi Saito,et al. Extracting regression rules from neural networks , 2002, Neural Networks.

[2] Tor Guimaraes,et al. Integrating artificial neural networks with rule-based expert systems , 1994, Decis. Support Syst..

[3] R. Brent. Table errata: Algorithms for minimization without derivatives (Prentice-Hall, Englewood Cliffs, N. J., 1973) , 1975 .

[4] Rua-Huan Tsaih. An explanation of reasoning neural networks , 1998 .

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

[6] Jacek M. Zurada,et al. Extraction of rules from artificial neural networks for nonlinear regression , 2002, IEEE Trans. Neural Networks.

[7] James R. Munkres,et al. Topology; a first course , 1974 .