Neural networks: Studying their decision-making rules
DOI:
https://doi.org/10.20535/SRIT.2308-8893.2023.2.06Keywords:
rule extraction, neural networks, DeepRED, machine learning, decision trees, decision graphsAbstract
The question of a better understanding of the behavior of neural networks is quite relevant, especially in industries with a high level of risks. To solve this problem, the possibilities of the new DeepRED decomposition algorithm, capable of extracting decision-making rules by deep neural networks with several hidden layers, are explored in the paper. The study of the DeepRED algorithm was carried out on the example of extracting the rules of an experimental neural network during the classification of images of the MNIST database of handwritten digits, which made it possible to reveal a number of limitations of the DeepRED algorithm.
References
Frank Emmert-Streib, Zhen Yang, Han Feng, Shailesh Tripathi, and Matthias Dehmer, “An Introductory Review of Deep Learning for Prediction Models With Big Data,” Front. Artif. Intell., 2020. Available: https://www.frontiersin.org/articles/10.3389/frai.2020.00004/full
H. Jacobsson, “Rule Extraction from Recurrent Neural Networks: A Taxonomy and Review,” Neural Computation, vol. 17, no. 6, pp. 1223–1263, 2005. Available: https://doi.org/10.1162/0899766053630350
A. Bondarenko, L. Aleksejeva, V. Jumutcs, and A. Borisovs, “Classification Tree Extraction from Trained Artificial Neural Networks,” Procedia Computer Science, vol. 104, pp. 556–563, 2017. Available: https://doi.org/10.1016/j.procs.2017.01.172
Hiroshi Tsukimoto, “Extracting rules from trained neural networks,” IEEE Transactions on Neural networks, 2000. Available: https://ieeexplore.ieee.org/document/839008
Ismail Taha and Joydeep Ghosh, “Symbolic interpretation of artificial neural networks,” Knowledge and Data Engineering, IEEE, 1999. Available: https://ieeexplore.ieee.org/document/774103
J.M. Benitez, J.L. Castro, and I. Requena, “Are artificial neural networks black boxes?” IEEE Transactions on Neural Networks, 1997. Available: https://ieeexplore.ieee.org/document/623216
J.R. Zilke, E.L. Mencia, and F. Janssen, “DeepRED–Rule extraction from deep neural networks,” in T. Calders, M. Ceci, D. Malerba (Eds.): Discovery Science 19th International Conference, DS 2016, Bari, Italy, Oct. 19–21, 2016, Proceedings, LNAI 9956, pp. 457-473, 2016. Available: https://doi.org/10.1007/978-3-319-46307-0_29
Kamal Kumar Sethi, Durgesh Kumar Mishra, and Bharat Mishra, “Extended Taxonomy of Rule Extraction Techniques and Assessment of KDRuleEx,” International Journal of Computer Applications, 2012. Available: https://www.researchgate.net/publication/258652014_Extended_Taxonomy_of_Rule_Extraction_Techniques_and_Assessment_of_KDRuleEx
Kamal Kumar Sethi, Durgesh Kumar Mishra, and Bharat Mishra, “KDRuleEx: A Novel Approach for Enhancing User Comprehensibility Using Rule Extraction,” Third International Conference on Intelligent Systems Modelling and Simulation, IEEE, 2012. Available: https://ieeexplore.ieee.org/document/6169675
LiMin Fu, “Rule generation from neural networks,” IEEE Transactions on Systems, Man, and Cybernetics, 1994. Available: https://ieeexplore.ieee.org/document/299696
M. Gethsiyal Augasta and Thangairulappan Kathirvalavakumar, “Reverse engineering the neural networks for rule extraction in classification problems,” Neural Processing Letters, 2012. Available: https://www.researchgate.net/publication/216628594_Reverse_Engineering_the_Neural_Networks_for_Rule_Extraction_in_Classification_Problems
Makoto Sato and Hiroshi Tsukimoto, “Rule extraction from neural networks via decision tree induction,” International Joint Conference on Neural Networks, IEEE, 2001. Available: https://ieeexplore.ieee.org/document/938448
Mark W. Craven and Jude W. Shavlik, “Extracting tree-structured representations of trained networks,” Advances in Neural Information Processing Systems, 1996. Available: https://proceedings.neurips.cc/paper/1995/file/45f31d16b1058d586fc3be7207b58053-Paper.pdf
Matej Fanta, Petr Pulc, and Martin Holena, Rules Extraction from Neural Networks Trained on Multimedia Data. 2019. Available: http://ceur-ws.org/Vol-2473/paper4.pdf
Rudy Setiono and Wee Kheng Leow, “FERNN: An algorithm for fast extraction of rules from neural networks,” Applied Intelligence, 2000. Available: https://link.springer.com/article/10.1023/A:1008307919726
Rudy Setiono, Extracting M-of-N Rules from Trained Neural Networks. National University of Singapore. Available: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.37.4104&rep=rep1&type=pdf
Sebastian Thrun, “Extracting provably correct rules from artificial neural networks,” Technical Report. University of Bonn, Institut für Informatik III, 1993. Available: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.31.9441
Sebastian Thrun, “Extracting rules from artificial neural networks with distributed representations,” Advances in Neural Information Processing Systems, 1995. Available: https://proceedings.neurips.cc/paper/1994/file/bea5955b308361a1b07bc55042e25e54-Paper.pdf
Tameru Hailesilassie, “Rule Extraction Algorithm for Deep Neural Networks: A Review,” International Journal of Computer Science and Information Security, vol. 14, no. 7, 2016. Available: https://arxiv.org/ftp/arxiv/papers/1610/1610.05267.pdf
Zhi-Hua Zhou, Shi-Fu Chen, and Zhao-Qian Chen, “A statistics based approach for extracting priority rules from trained neural networks,” International Joint Conference on Neural Networks, IEEE, 2000. Available: https://ieeexplore.ieee.org/document/861337
S.L. Salzberg, C4.5: Programs for Machine Learning by Quinlan J. Ross Quinlan. Morgan Kaufmann Publishers, Inc., 1993, pp. 38–48. Available: https://doi.org/10.1007/BF00993309
Geoffrey E. Hinton, Simon Osindero, and Yee-Whye Teh, “A fast learning algorithm for deep belief nets,” Neural Computation, 2006.
Daniel Etzold, MNIST — Dataset of Handwritten Digits. 2015. Available: https://medium.com/mlearning-ai/mnist-dataset-of-handwritten-digits-f8cf28edafe