Abstract
The paper focuses on the problem of rule extraction from neural networks, with the aim of transforming the knowledge captured in a trained neural network into a familiar form for human user. The ultimate purpose for us is to develop human friendly shells for neural network based systems. In the first part of the paper it is presented an approach on extracting traditional crisp rules out of the neural networks, while the last part of the paper presents how to transform the neural network into a set of fuzzy rules using an interactive fuzzy operator. The rules are extracted from ordinary neural networks, which have not a structure that facilitate the rule extraction. The neural network trained with the well known Iris data set was considered as benchmark problem.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Benitez, J.M., Blanco, A., Delgado, M., Requena, I.: Neural methods for obtaining fuzzy rules. Mathware Soft Computing, vol.3 (1996) 371–382
Ishigami, H., Fukuda, T., Shibata, T., Arai, F.: Structure Optimization of Fuzzy Neural Networks by Genetic Algorithm. Fuzzy Sets and System 71 (1995) 257–265
Kosko, B.: Neural Networks and Fuzzy Systems. Prentice-Hall International Inc. (1992)
Lin, C.T., George Lee, C.S.: Neural-Network Based Fuzzy Logic Control and Decision System. IEEE Transactions on Computers, vol. 40 No. 12 (1991) 1320–1336
Neagu, C.D., Palade, V.: An interactive fuzzy operator used in rule extraction from neural networks. Neural Network World 4, Prague (2000) 675–684
Palade, V., Neagu, C.D., Negoita, M.: Genetic algorithm optimization of knowledge extraction from neural networks. Proceedings of the 6th International Conference on Neural Information Processing, Perth-Australia, vol. 2 (1999) 765–770
Palade, V., Neagu, C.D., Puscasu, G.: Rule extraction from neural networks by interval propagation. Proceedings of the 4th IEEE International Conference on Knowledge-Based Intelligent Engineering Systems & Allied Technologies-KES2000, Brighton-UK (2000) 217–220
Palade, V., Puscasu, G., Neagu, C.D.: Neural network-based control by inverting neural models. Control Engineering and Applied Informatics, no. 1, vol. 1, Bucharest (1999) 25–31
Patton, R.J., Uppal, F.J., Lopez-Toribio, C.J.: Soft computing aproaches to fault diagnosis for dynamic systems: a survey. Proceedings of the 4th IFAC Symposium on Fault Detection Supervision and Safety for Technical Processes, Budapest, vol. 1 (2000) 298–311
Pinkas, G.: Logical Inference in Symmetric Connectionist Networks. Ph.D. thesis, Washington University (1992)
Scott, G.M.: Knowledge-Based Artificial Neural Networks for Process Modeling and Control. Ph.D. thesis, University of Wisconsin (1993)
Shann, J.J., Fu, H.C.: A fuzzy neural network for rule acquiring on fuzzy control systems. Fuzzy Sets and Systems 71 (1995) 345–357
Thrun, S.B.: Extracting Symbolic Knowledge from Artificial Neural Networks. Revised Version of Technical Research Report TR-IAI-93-5, Institut für Informatik III-Universität Bonn (1994)
Towell, G., Shavlik, J.W.: The Extraction of Refined Rules from Knowledge-Based Neural Networks. Machine-Learning, vol.13 (1993)
Yoo, J.H.: Symbolic Rule Extraction from Artificial Neural Networks. Ph.D. thesis, Wayne State University (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Palade, V., Neagu, DC., Patton, R.J. (2001). Interpretation of Trained Neural Networks by Rule Extraction. In: Reusch, B. (eds) Computational Intelligence. Theory and Applications. Fuzzy Days 2001. Lecture Notes in Computer Science, vol 2206. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45493-4_20
Download citation
DOI: https://doi.org/10.1007/3-540-45493-4_20
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42732-2
Online ISBN: 978-3-540-45493-9
eBook Packages: Springer Book Archive