Abstract
Deep neural networks are accurate predictors, but their decisions are difficult to interpret, which limits their applicability in various fields. Symbolic representations in the form of rule sets are one way to illustrate their behavior as a whole, as well as the hidden concepts they model in the intermediate layers. The main contribution of the paper is to demonstrate how to facilitate rule extraction from a deep neural network by retraining it in order to encourage sparseness in the weight matrices and make the hidden units be either maximally or minimally active. Instead of using datasets which combine the attributes in an unclear manner, we show the effectiveness of the methods on the task of reconstructing predefined Boolean concepts so it can later be assessed to what degree the patterns were captured in the rule sets. The evaluation shows that reducing the connectivity of the network in such a way significantly assists later rule extraction, and that when the neurons are either minimally or maximally active it suffices to consider one threshold per hidden unit.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
References
Aizenberg, I., Aizenberg, N.N., Vandewalle, J.P.: Multi-valued and Universal Binary Neurons: Theory, Learning and Applications. Springer, New York (2013). doi:10.1007/978-1-4757-3115-6
Andrews, R., Diederich, J., Tickle, A.B.: Survey and critique of techniques for extracting rules from trained artificial neural networks. Knowl. Based Syst. 8(6), 373–389 (1995)
Courbariaux, M., Bengio, Y., David, J.: BinaryConnect: training deep neural networks with binary weights during propagations. In: Advances in Neural Information Processing Systems 28 (NIPS 2015), Montreal, Quebec, Canada, pp. 3123–3131 (2015)
Craven, M., Shavlik, J.W.: Using sampling and queries to extract rules from trained neural networks. In: Proceedings of the 11th International Conference on Machine Learning (ICML 1994), pp. 37–45. Morgan Kaufmann, New Brunswick (1994)
Craven, M., Shavlik, J.W.: Extracting tree-structured representations of trained networks. In: Advances in Neural Information Processing Systems 8 (NIPS 1995), pp. 24–30 (1995)
Demšar, J., Schuurmans, D.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7(1), 1–30 (2006)
Freitas, A.A.: Comprehensible classification models: a position paper. SIGKDD Explor. 15(1), 1–10 (2013)
Fu, L.: Rule learning by searching on adapted nets. In: Proceedings of the 9th National Conference on Artificial Intelligence (AAAI 1991), Anaheim, CA, USA, vol. 2, pp. 590–595 (1991)
Fürnkranz, J., Gamberger, D., Lavrač, N.: Foundations of Rule Learning. Springer, Heidelberg (2012). doi:10.1007/978-3-540-75197-7
Goodfellow, I.J., Bengio, Y., Courville, A.C.: Deep Learning. Adaptive Computation and Machine Learning. MIT Press, Cambridge (2016)
Han, S., Pool, J., Tran, J., Dally, W.J.: Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems 28 (NIPS 2015), Montreal, Quebec, Canada, pp. 1135–1143 (2015)
Hassibi, B., Stork, D.G.: Second order derivatives for network pruning: optimal brain surgeon. In: Advances in Neural Information Processing Systems 5 (NIPS 1992), pp. 164–171. Morgan Kaufmann, Denver (1992)
Hayes, J.P.: Digital Logic Design. Addison Wesley, Reading (1993)
Kayande, U., Bruyn, A.D., Lilien, G.L., Rangaswamy, A., van Bruggen, G.H.: How incorporating feedback mechanisms in a DSS affects DSS evaluations. Inf. Syst. Res. 20(4), 527–546 (2009)
LeCun, Y., Denker, J.S., Solla, S.A.: Optimal brain damage. In: Advances in Neural Information Processing Systems 2 (NIPS 1990), Denver, Colorado, USA, pp. 598–605 (1989)
Liu, J., Li, M.: Finding cancer biomarkers from mass spectrometry data by decision lists. J. Comput. Biol. 12(7), 971–979 (2005)
Malioutov, D.M., Varshney, K.R.: Exact rule learning via Boolean compressed sensing. In: Proceedings of the 30th International Conference on Machine Learning (ICML 2013), Atlanta, GA, USA, pp. 765–773 (2013)
Milaré, C.R., Carvalho, A.C.P.L.F., Monard, M.C.: Extracting knowledge from artificial neural networks: an empirical comparison of trepan and symbolic learning algorithms. In: Coello Coello, C.A., Albornoz, A., Sucar, L.E., Battistutti, O.C. (eds.) MICAI 2002. LNCS (LNAI), vol. 2313, pp. 272–281. Springer, Heidelberg (2002). doi:10.1007/3-540-46016-0_29
Ng, A.: Sparse autoencoder. CS294A Lecture Notes, Stanford University (2011)
Sato, M., Tsukimoto, H.: Rule extraction from neural networks via decision tree induction. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN 2001), vol. 3, pp. 1870–1875. IEEE Press (2001)
Setiono, R.: Extracting rules from pruned neural networks for breast cancer diagnosis. Artif. Intell. Med. 8(1), 37–51 (1996)
Setiono, R.: Extracting rules from neural networks by pruning and hidden-unit splitting. Neural Comput. 9(1), 205–225 (1997)
Setiono, R.: A penalty-function approach for pruning feedforward neural networks. Neural Comput. 9(1), 185–204 (1997)
Setiono, R., Liu, H.: Symbolic representation of neural networks. IEEE Comput. 29(3), 71–77 (1996)
Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Thodberg, H.H.: Improving generalization of neural networks through pruning. Int. J. Neural Syst. 1(4), 317–326 (1991)
Towell, G.G., Shavlik, J.W.: Extracting refined rules from knowledge-based neural networks. Mach. Learn. 13(1), 71–101 (1993)
Tsukimoto, H.: Extracting rules from trained neural networks. IEEE Trans. Neural Netw. Learn. Syst. 11(2), 377–389 (2000)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). doi:10.1007/978-3-319-10590-1_53
Zilke, J.R., Loza Mencía, E., Janssen, F.: DeepRED - rule extraction from deep neural networks. In: Proceedings of the 19th International Conference on Discovery Science (DS 2016), Bari, Italy, pp. 457–473 (2016)
Acknowledgements
We would like to thank the anonymous reviewers for their helpful suggestions. Computations for this research were conducted on the Lichtenberg high performance computer of the TU Darmstadt.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
González, C., Loza Mencía, E., Fürnkranz, J. (2017). Re-training Deep Neural Networks to Facilitate Boolean Concept Extraction. In: Yamamoto, A., Kida, T., Uno, T., Kuboyama, T. (eds) Discovery Science. DS 2017. Lecture Notes in Computer Science(), vol 10558. Springer, Cham. https://doi.org/10.1007/978-3-319-67786-6_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-67786-6_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67785-9
Online ISBN: 978-3-319-67786-6
eBook Packages: Computer ScienceComputer Science (R0)