论文信息 - Extracting Rules from Neural Networks: a

Extracting Rules from Neural Networks: a

This paper discusses how rule extraction from Artificial Neural Networks (ANNs) can help in the design of expert systems and in the application of RNAs as a data mining technique. Examples of methods of rule extraction from RNAs are given in the paper.

Antônio de Pádua Braga | Teresa B. Ludermir | Belo Horizonte-MG | Cristiane N. Nobre | Andre P. L. Carvalho

[1] Huan Liu,et al. Understanding Neural Networks via Rule Extraction , 1995, IJCAI.

[2] Mark Craven,et al. Extracting comprehensible models from trained neural networks , 1996 .

[3] Jude W. Shavlik,et al. Learning Symbolic Rules Using Artificial Neural Networks , 1993, ICML.

[4] LiMin Fu,et al. Rule Learning by Searching on Adapted Nets , 1991, AAAI.

[5] Reinhard Blasig. GDS: Gradient Descent Generation of Symbolic Classification Rules , 1993, NIPS.

[6] Michael C. Mozer,et al. Rule Induction through Integrated Symbolic and Subsymbolic Processing , 1991, NIPS.

[7] Jude W. Shavlik,et al. Using Sampling and Queries to Extract Rules from Trained Neural Networks , 1994, ICML.

[8] Sukhdev Khebbal,et al. Intelligent Hybrid Systems , 1994 .

[9] Stephen I. Gallant,et al. Connectionist expert systems , 1988, CACM.

[10] Sebastian Thrun,et al. The MONK''s Problems-A Performance Comparison of Different Learning Algorithms, CMU-CS-91-197, Sch , 1991 .