Abstract
Artificial Neural Networks are considered as a black box. They are unable to explain its classification decision. Several rule extraction algorithms from trained neural networks have been developed to overcome this problem. The aim is to have a set of rules to explain how ANNs solves a given problem. A global rule extraction algorithm from trained neural networks, based on evolutionary algorithms is presented. The extracted rules are evaluated from three criteria: fidelity, accuracy and comprehensibility. The fidelity indicates how the extracted rules mimic the decision of the trained neural networks. The accuracy is calculated from dataset, it indicates the ability of the rules to satisfy the test data. The comprehensibility designates the number of the extracted rules. The proposed method is evaluated on 03 UCI datasets. A tradeoff between the accuracy, the fidelity and the comprehensibility has been showed. The results of these experiments are presented and compared with existing rule extraction methods. Our proposal achieves a best accuracy and comprehensibility over breast cancer dataset.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lin, W.Y., Tseng, M.C., Su, J.H.: A confidence-lift support specification for interesting associations mining. In: PAKDD, pp. 148–158 (2002)
Fu, L.: Integration of neural heuristics into knowledge-based inference. Conn. Sci. 1(3), 325–340 (1989)
Towel, G.G., Shavlik, J.W.: Knowledge based artificial neural networks. Artif. Intell. 9(1) (1994)
Sestito, S., Dillon, T.: Knowledge acquisition of conjunctive rules using multilayered neural networks. Int. J. Intell. Syst. 8, 779–805 (1993)
Setiono, R.: Extracting rules from neural networks by pruning and hidden-unit splitting. Neural Comput. 9, 205–225 (1997)
Thrun, S.B.: Advances in Neural Information Processing Systems. MIT, San Mateo (1995)
Craven, M., Shavlik, J.: Extracting tree-structured representations of trained networks. Adv. Neural. Inf. Process. Syst. 8, 24–30 (1996)
Taha, I., Ghosh, J.: Symbolic interpretation of artificial neural networks. Technical report TR-97-01-106, University of Texas, Austin (1996)
Markowska-Kaczmar, U., Chumieja, M.: Discovering the mysteries of neural networks. Int. J. Hybrid Intell. Syst. 1(3/4), 153–163 (2004)
Markowska-Kaczmar, U.: Evolutionary approaches to rule extraction from neural networks. In: Studies in Computational Intelligence (SCI), vol. 82, pp. 177–209 (2008)
Markowska-Kaczmar, U., Wnuk-Lipinski, P.: Rule extraction from neural network by genetic algorithm with pareto optimization. In: Rutkowski, L. (ed.) Artificial Intelligence and Soft Computing, pp. 450–455 (2004)
Markowska-Kaczmar, U., Mularczyk, K.: GA-based rule extraction from neural networks for approximation. In: Proceedings of the International Multiconference on Computer Science and Information Technology, pp. 141–148 (2006)
Santos, R., Nievola, J., Freitas, A.: Extracting comprehensible rules from neural networks via genetic algorithm. In: Proceedings of 2000 IEEE Symposium on Combination of Evolutionary Algorithm and Neural Network. S. Antonio, RX, USA, pp. 130–139 (2000)
Huysmans, J., Baesens, B., Vanthienen, J.: Using rule extraction to improve the comprehensibility of predictive models (2006). SSRN: http://ssrn.com/abstract=961358 or http://dx.doi.org/10.2139/ssrn.961358
Deb, K.: Multi-Objective Optimization Using Evolutionary Algorithms. Wiley, Hoboken (2001)
Yedjour, D., Benyettou, A.: Symbolic interpretation of artificial neural networks based on multiobjective genetic algorithms and association rules mining. Appl. Soft Comput. 72, 177–188 (2018)
Shinde, S., Kulkarni, U.: Extracting classification rules from modified fuzzy min–max neural network for data with mixed attributes. Appl. Soft Comput. 40, 364–378 (2016)
Hayashi, Y., Yukita, S.: Rule extraction using recursive-rule extraction algorithm with J48graft combined with sampling selection techniques for the diagnosis of type 2 diabetes mellitus in the Pima Indian dataset. Inf. Med. Unlock. 2, 92–104 (2016)
Hayashi, Y., Setiono, R., Azcarraga, A.: Neural network training and rule extraction with augmented discretized input. Neurocomputing 207, 610–622 (2016)
Setiono, R., Liu, H.: Understanding neural networks via rule extraction. In: Proceedings of the 14th International Joint Conference on Artificial Intelligence (IJCAI), pp 480–485 (1995)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yedjour, D. (2021). Application of the Genetic Algorithm to the Rule Extraction Problem. In: Hatti, M. (eds) Artificial Intelligence and Renewables Towards an Energy Transition. ICAIRES 2020. Lecture Notes in Networks and Systems, vol 174. Springer, Cham. https://doi.org/10.1007/978-3-030-63846-7_57
Download citation
DOI: https://doi.org/10.1007/978-3-030-63846-7_57
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63845-0
Online ISBN: 978-3-030-63846-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)