Skip to main content
SpringerLink
Log in
Book cover

International Conference on Discovery Science

DS 2017: Discovery Science pp 127–143Cite as

Re-training Deep Neural Networks to Facilitate Boolean Concept Extraction

  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 10558))

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.

This is a preview of subscription content, log in via an institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Notes

  1. 1.

    EU Regulation 2016/679: http://eur-lex.europa.eu/eli/reg/2016/679/oj, http://www.eugdpr.org.

  2. 2.

    http://www.europarl.europa.eu/oeil/popups/ficheprocedure.do?reference=2015/2103(INL).

References

  1. 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

    MATH  Google Scholar 

  2. 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)

    Article  MATH  Google Scholar 

  3. 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)

    Google Scholar 

  4. 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)

    Google Scholar 

  5. 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)

    Google Scholar 

  6. Demšar, J., Schuurmans, D.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7(1), 1–30 (2006)

    MathSciNet  MATH  Google Scholar 

  7. Freitas, A.A.: Comprehensible classification models: a position paper. SIGKDD Explor. 15(1), 1–10 (2013)

    Article  Google Scholar 

  8. 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)

    Google Scholar 

  9. Fürnkranz, J., Gamberger, D., Lavrač, N.: Foundations of Rule Learning. Springer, Heidelberg (2012). doi:10.1007/978-3-540-75197-7

    Book  MATH  Google Scholar 

  10. Goodfellow, I.J., Bengio, Y., Courville, A.C.: Deep Learning. Adaptive Computation and Machine Learning. MIT Press, Cambridge (2016)

    MATH  Google Scholar 

  11. 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)

    Google Scholar 

  12. 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)

    Google Scholar 

  13. Hayes, J.P.: Digital Logic Design. Addison Wesley, Reading (1993)

    Google Scholar 

  14. 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)

    Article  Google Scholar 

  15. 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)

    Google Scholar 

  16. Liu, J., Li, M.: Finding cancer biomarkers from mass spectrometry data by decision lists. J. Comput. Biol. 12(7), 971–979 (2005)

    Article  Google Scholar 

  17. 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)

    Google Scholar 

  18. 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

    Chapter  Google Scholar 

  19. Ng, A.: Sparse autoencoder. CS294A Lecture Notes, Stanford University (2011)

    Google Scholar 

  20. 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)

    Google Scholar 

  21. Setiono, R.: Extracting rules from pruned neural networks for breast cancer diagnosis. Artif. Intell. Med. 8(1), 37–51 (1996)

    Article  Google Scholar 

  22. Setiono, R.: Extracting rules from neural networks by pruning and hidden-unit splitting. Neural Comput. 9(1), 205–225 (1997)

    Article  MATH  Google Scholar 

  23. Setiono, R.: A penalty-function approach for pruning feedforward neural networks. Neural Comput. 9(1), 185–204 (1997)

    Article  MATH  Google Scholar 

  24. Setiono, R., Liu, H.: Symbolic representation of neural networks. IEEE Comput. 29(3), 71–77 (1996)

    Article  Google Scholar 

  25. 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)

    MathSciNet  MATH  Google Scholar 

  26. Thodberg, H.H.: Improving generalization of neural networks through pruning. Int. J. Neural Syst. 1(4), 317–326 (1991)

    Article  Google Scholar 

  27. Towell, G.G., Shavlik, J.W.: Extracting refined rules from knowledge-based neural networks. Mach. Learn. 13(1), 71–101 (1993)

    Google Scholar 

  28. Tsukimoto, H.: Extracting rules from trained neural networks. IEEE Trans. Neural Netw. Learn. Syst. 11(2), 377–389 (2000)

    Article  Google Scholar 

  29. 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

    Google Scholar 

  30. 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)

    Google Scholar 

Download references

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

  1. Knowledge Engineering Group, TU Darmstadt, Hochschulstrasse 10, 64289, Darmstadt, Germany

    Camila González, Eneldo Loza Mencía & Johannes Fürnkranz

Authors
  1. Camila González
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Eneldo Loza Mencía
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Johannes Fürnkranz
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Camila González .

Editor information

Editors and Affiliations

  1. Kyoto University, Kyoto, Japan

    Akihiro Yamamoto

  2. Hokkaido University, Sapporo, Japan

    Takuya Kida

  3. National Institute of Informatics, Tokyo, Japan

    Takeaki Uno

  4. Gakushuin University, Tokyo, Japan

    Tetsuji Kuboyama

Rights and permissions

Reprints 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)

Publish with us

Policies and ethics

Search

Navigation