Extracting comprehensible models from trained neural networks
- Author:
- Mark William Craven,
- Supervisor:
- Jude W. Shavlik
Abstract
No abstract available.
Cited By
Zhang Y, Yao T, Qiu Z and Mei T (2023). Explaining Cross-domain Recognition with Interpretable Deep Classifier, ACM Transactions on Multimedia Computing, Communications, and Applications, 20:3, (1-21), Online publication date: 31-Mar-2024.- Haldar S, Saha D, Wei D, Nair R and Daly E Interpretable differencing of machine learning models Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, (788-797)
- Ramon Y, Martens D, Provost F and Evgeniou T (2020). A comparison of instance-level counterfactual explanation algorithms for behavioral and textual data: SEDC, LIME-C and SHAP-C, Advances in Data Analysis and Classification, 14:4, (801-819), Online publication date: 1-Dec-2020.
- Fernandez A, Herrera F, Cordon O, Jose del Jesus M and Marcelloni F (2019). Evolutionary Fuzzy Systems for Explainable Artificial Intelligence, IEEE Computational Intelligence Magazine, 14:1, (69-81), Online publication date: 1-Feb-2019.
- Vidulin V, Bohanec M and Gams M (2014). Combining human analysis and machine data mining to obtain credible data relations, Information Sciences: an International Journal, 288:C, (254-278), Online publication date: 20-Dec-2014.
- Kulluk S, ÖZbakıR L and BaykasoğLu A (2013). Fuzzy DIFACONN-miner, Expert Systems with Applications: An International Journal, 40:3, (938-946), Online publication date: 1-Feb-2013.
- Stumpf S, Burnett M, Pipek V and Wong W End-user interactions with intelligent and autonomous systems CHI '12 Extended Abstracts on Human Factors in Computing Systems, (2755-2758)
- Yeh Y, Hou T and Chang W (2012). An intelligent model for the classification of children's occupational therapy problems, Expert Systems with Applications: An International Journal, 39:5, (5233-5242), Online publication date: 1-Apr-2012.
- Mohamed M (2011). Rules extraction from constructively trained neural networks based on genetic algorithms, Neurocomputing, 74:17, (3180-3192), Online publication date: 1-Oct-2011.
- Ruiz W and Guzman E Fraud detection model based on the discovery symbolic classification rules extracted from a neural network Proceedings of the 9th Mexican international conference on Artificial intelligence conference on Advances in soft computing: Part II, (290-302)
- de Oliveira D, de Oliveira Andrade A, Nobre C and Zárate L The usage of artificial neural networks in the classification and forecast of potable water consumption Proceedings of the 2009 international joint conference on Neural Networks, (2334-2341)
- Liang P, Daumé H and Klein D Structure compilation Proceedings of the 25th international conference on Machine learning, (592-599)
- Assche A and Blockeel H Seeing the Forest Through the Trees Proceedings of the 18th European conference on Machine Learning, (418-429)
- Esmeir S and Markovitch S (2007). Anytime Learning of Decision Trees, The Journal of Machine Learning Research, 8, (891-933), Online publication date: 1-May-2007.
- Van Assche A and Blockeel H Seeing the forest through the trees Proceedings of the 17th international conference on Inductive logic programming, (269-279)
- Esmeir S and Markovitch S When a decision tree learner has plenty of time proceedings of the 21st national conference on Artificial intelligence - Volume 2, (1597-1600)
- Esmeir S and Markovitch S Any time induction of decision trees Proceedings of the 21st national conference on Artificial intelligence - Volume 1, (348-355)
- Esmeir S and Markovitch S Interruptible anytime algorithms for iterative improvement of decision trees Proceedings of the 1st international workshop on Utility-based data mining, (78-85)
- Torres D. D and Rocco S. C A comparative study for assessing the reliability of complex networks using rules extracted from different machine learning approaches Proceedings of the 18th Australian Joint conference on Advances in Artificial Intelligence, (954-958)
- Estruch V, Ferri C, Hernández-Orallo J and Ramírez-Quintana M Simple mimetic classifiers Proceedings of the 3rd international conference on Machine learning and data mining in pattern recognition, (156-171)
- Boz O Extracting decision trees from trained neural networks Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, (456-461)
- Domingos P Machine learning Handbook of data mining and knowledge discovery, (660-670)
- Wermter S (2019). Knowledge Extraction from Transducer Neural Networks, Applied Intelligence, 12:1-2, (27-42), Online publication date: 1-Jan-2000.
- Paass G and Kindermann J Transparency and Predicive Power Proceedings of the 4th European Conference on Principles of Data Mining and Knowledge Discovery, (558-565)
- Fanni A, Giua A, Marchesi M and Montisci A (1999). A Neural Network Diagnosis Approach for Analog Circuits, Applied Intelligence, 11:2, (169-186), Online publication date: 1-Sep-1999.
- Domingos P (1999). The Role of Occam‘s Razor in Knowledge Discovery, Data Mining and Knowledge Discovery, 3:4, (409-425), Online publication date: 1-Dec-1999.
- Provost F and Kolluri V (1999). A Survey of Methods for Scaling Up Inductive Algorithms, Data Mining and Knowledge Discovery, 3:2, (131-169), Online publication date: 1-Jun-1999.
- Domingos P Occam's two razors Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining, (37-43)
- Averkin A Hybrid Intelligent Systems Based on Fuzzy Logic and Deep Learning Artificial Intelligence, (3-12)
Recommendations
Extracting symbolic rules from trained neural network ensembles
Artificial Intelligence Advances in ChinaNeural network ensemble can significantly improve the generalization ability of neural network based systems. However, its comprehensibility is even worse than that of a single neural network because it comprises a collection of individual neural ...
Extracting symbolic rules from trained neural network ensembles
Special issue on Artificial intelligence advances in ChinaNeural network ensemble can significantly improve the generalization ability of neural network based systems. However, its comprehensibility is even worse than that of a single neural network because it comprises a collection of individual neural ...
Extracting rules from trained neural networks
Presents an algorithm for extracting rules from trained neural networks. The algorithm is a decompositional approach which can be applied to any neural network whose output function is monotone such as a sigmoid function. Therefore, the algorithm can be ...