Advertisement

Interpretable Machine Learning from Granular Computing Perspective

  • Raúl Navarro-AlmanzaEmail author
  • Juan R. Castro
  • Mauricio A. Sanchez
Chapter
Part of the Studies in Systems, Decision and Control book series (SSDC, volume 209)

Abstract

Machine Learning (ML) is a method that aims to learn from data to identify patterns and make predictions. Nowadays ML models have become ubiquitous, there are so many services that people use in their daily life, consequently, those systems affect in very ways to the final users. Recently, there is a special interest on the right of the final user to know why the system generates some output; this field is called Interpretable Machine Learning (IML). Granular Computing (GrC) paradigm is focused in knowledge modeling inspired by human thinking. In this work we conduct a survey of the state of the art in IML and GrC fields to settle the bases of the possible contribution of each other with aims to build more interpretable and accurately ML models.

Keywords

Interpretable machine learning Granular computing Explainable artificial intelligence 

Notes

Acknowledgements

This research was partially supported by MyDCI (Maestría y Doctorado en Ciencias e Ingeniería).

References

  1. 1.
    Arras, L., et al.: “What is relevant in a text document?”: an interpretable machine learning approach. PLoS ONE 12(8) (2017). ISSN 19326203.  https://doi.org/10.1371/journal.pone.0181142CrossRefGoogle Scholar
  2. 2.
    Bargiela, A., Pedrycz, W.: Granular Computing (2003). ISBN 978-1-4613-5361-4.  https://doi.org/10.1007/978-1-4615-1033-8CrossRefGoogle Scholar
  3. 3.
    Basu, S., et al.: Iterative random forests to discover predictive and stable high-order interactions. Proc. Natl. Acad. Sci. U.S.A. 115(8), 1943–1948 (2018). ISSN 00278424.  https://doi.org/10.1073/pnas.1711236115MathSciNetCrossRefGoogle Scholar
  4. 4.
    Beaton, B.: Crucial answers about humanoid capital. In: ACM/IEEE International Conference on Human-Robot Interaction, pp. 5–12. IEEE Computer Society (2018). ISBN 9781450356152.  https://doi.org/10.1145/3173386.3173391
  5. 5.
    Belle, V.: Logic meets probability: towards explainable AI systems for uncertain worlds. In: IJCAI International Joint Conference on Artificial Intelligence, pp. 5116–5120 (2017). ISSN 10450823.  https://doi.org/10.24963/ijcai.2017/733
  6. 6.
    Brinkrolf, J., Hammer, B.: Interpretable machine learning with reject option. At-Automatisierungstechnik 66(4), 283–290 (2018). ISSN 01782312.  https://doi.org/10.1515/auto-2017-0123CrossRefGoogle Scholar
  7. 7.
    Caywood, M.S., et al.: Gaussian process regression for predictive but interpretable machine learning models: an example of predicting mental workload across tasks. Front. Hum. Neurosci. 10 (2017). ISSN 16625161.  https://doi.org/10.3389/fnhum.2016.00647
  8. 8.
    Ding, S., et al.: Granular neural networks. Artif. Intell. Rev. 1(3), 373–384 (2014). ISSN 02692821.  https://doi.org/10.1007/s10462-012-9313-7CrossRefGoogle Scholar
  9. 9.
    Goodman, B., Flaxman, S.: European Union regulations on algorithmic decision-making and a “right to explanation”, pp. 1–9 (2016). ISSN 0738-4602.  https://doi.org/10.1609/aimag.v38i3.2741. arXiv: 1606.08813CrossRefGoogle Scholar
  10. 10.
    Guo, H., Wang, W.: Granular support vector machine: a review. Artif. Intell. Rev. 51(1), 19–32 (2019). ISSN 15737462.  https://doi.org/10.1007/s10462-017-9555-5MathSciNetCrossRefGoogle Scholar
  11. 11.
    Hofmann, D., et al.: Learning interpretable kernelized prototype-based models. Neurocomputing 141, 84–96 (2014). ISSN 09252312.  https://doi.org/10.1016/j.neucom.2014.03.003CrossRefGoogle Scholar
  12. 12.
    Huang, S.H., et al.: Enabling robots to communicate their objectives. Auton. Robots 1–18 (2018). ISSN 09295593.  https://doi.org/10.1007/s10514-018-9771-0CrossRefGoogle Scholar
  13. 13.
    Kim, B., Khanna, R., Koyejo, O.O.: Examples are not enough, learn to criticize! Criticism for interpretability. In: Lee, D.D., et al. (eds.) Advances in Neural Information Processing Systems, vol. 29, pp. 2280–2288. Curran Associates, Inc. (2016)Google Scholar
  14. 14.
    Lakkaraju, H., Bach, S.H., Leskovec, J.: Interpretable decision sets: a joint framework for description and prediction. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 13–17 August, pp. 1675–1684. Association for Computing Machinery (2016). ISBN 9781450342322.  https://doi.org/10.1145/2939672.2939874
  15. 15.
    Li, X., et al.: Using machine learning models to predict in-hospital mortality for ST-elevation myocardial infarction patients. In: Marie-Christine, J., Dong-sheng, Z., Gundlapalli, A.V. (eds.) Studies in Health Technology and Informatics, vol. 245, pp. 476–480 (2017). ISSN 18798365.  https://doi.org/10.3233/978-1-61499-830-3-476
  16. 16.
    Loia, V., Tomasiello, S.: Granularity into functional networks. In: 2017 3rd IEEE International Conference on Cybernetics, CYB-CONF 2017—Proceedings (2017).  https://doi.org/10.1109/CYBConf.2017.7985781
  17. 17.
    Mencar, C., Fanelli, A.M.: Interpretability constraints for fuzzy information granulation. Inf. Sci. 178(24), 4585–4618 (2008). ISSN 00200255.  https://doi.org/10.1016/j.ins.2008.08.015MathSciNetCrossRefGoogle Scholar
  18. 18.
    Miller, T.: Explanation in artificial intelligence: insights from the social sciences (2017). arXiv: 1706.07269
  19. 19.
    Molnar, C.: Interpretable Machine Learning. https://christophm.github.io/interpretable-ml-book/ (2019)
  20. 20.
    Nápoles, G., et al.: Fuzzy-rough cognitive networks. Neural Netw. 97, 19–27 (2018). ISSN 18792782.  https://doi.org/10.1016/j.neunet.2017.08.007CrossRefGoogle Scholar
  21. 21.
    Pal, S.K., Ray, S.S., Ganivada, A.: Granular Neural Networks, Pattern Recognition and Bioinformatics (2010). ISBN: 9783319571133Google Scholar
  22. 22.
    Panoutsos, G., Mahfouf, M.: A neural-fuzzy modelling frame-work based on granular computing: concepts and applications. Fuzzy Sets Syst. 161(21), 2808–2830 (2010). ISSN 01650114.  https://doi.org/10.1016/j.fss.2010.06.004MathSciNetCrossRefGoogle Scholar
  23. 23.
    Pedrycz, W., Chen, S.-M.: Granular Computing and Intelligent Systems, p. 305 (2011). ISBN 9783642017988.  https://doi.org/10.1007/978-3-642-19820-5zbMATHGoogle Scholar
  24. 24.
    Ribeiro, M.T., Singh, S., Guestrin, C.: “Why should I trust you?”: explaining the predictions of any classifier (2016). ISSN 9781450321389.  https://doi.org/10.1145/1235. arXiv: 1602.04938
  25. 25.
    Shalaeva, V., et al.: Multi-operator decision trees for explainable time-series classification. In: Verdegay, J.L., Pelta, D.A., Yager, R.R., Bouchon-Meunier, B., Medina, J., Ojeda-Aciego, M., Cabrera, I.P. (eds.) Communications in Computer and Information Science, vol. 853, pp. 86–99 (2018). ISSN 18650929.  https://doi.org/10.1007/978-3-319-91473-2_8Google Scholar
  26. 26.
    Smith, A., Nolan, J.J.: The problem of explanations with-out user feedback. In: CEUR Workshop Proceedings, vol. 2068 (2018). ISSN 16130073Google Scholar
  27. 27.
    Valdes, G., et al.: MediBoost: a patient stratification tool for interpretable decision making in the era of precision medicine. Sci. Rep. 6 (2016). ISSN 20452322.  https://doi.org/10.1038/srep37854
  28. 28.
    Varshney, K.R.: Interpretable machine learning via convex cardinal shape composition. In: 54th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2016, pp. 327–330. Institute of Electrical and Electronics Engineers Inc. (2017). ISBN 9781509045495.  https://doi.org/10.1109/ALLERTON.2016.7852248
  29. 29.
    Varshney, K.R.: Engineering safety in machine learning (2016). arXiv:1601.04126 [stat.ML]
  30. 30.
    van der Waa, J., et al.: ICM: an intuitive model independent and accurate certainty measure for machine learning. In: Rocha, A.P., van den Herik, J. (eds.) ICAART 2018—Proceedings of the 10th International Conference on Agents and Artificial Intelligence, vol. 2, pp. 314–321. SciTePress (2018). ISBN 9789897582752Google Scholar
  31. 31.
    Wang, T., et al.: Bayesian rule sets for interpretable classification. In: Baeza-Yates, R., Domingo-Ferrer, J., Zhou, Z.-H., Bonchi, F., Wu, X. (eds.) Proceedings—IEEE International Conference on Data Mining, ICDM, pp. 1269–1274. Institute of Electrical and Electronics Engineers Inc. (2017). ISBN 9781509054725.  https://doi.org/10.1109/ICDM.2016.130
  32. 32.
    Williams, J.J., et al.: Enhancing online problems through instructor-centered tools for randomized experiments. In: Conference on Human Factors in Computing Systems—Proceedings, Apr 2018. Association for Computing Machinery (2018). ISBN 9781450356206; 9781450356213.  https://doi.org/10.1145/3173574.3173781
  33. 33.
    Xu, X., et al.: A new method for constructing granular neural networks based on rule extraction and extreme learning machine. Pattern Recognit. Lett. 67, 138–144 (2015). ISSN 01678655.  https://doi.org/10.1016/j.patrec.2015.05.006CrossRefGoogle Scholar
  34. 34.
    Zadeh, L.A.: Fuzzy sets. Inf. Control 8(3), 338–353 (1965). ISSN 0019-9958.  https://doi.org/10.1016/S0019-9958(65)90241-XMathSciNetCrossRefGoogle Scholar
  35. 35.
    Zhu, X., Pedrycz, W., Li, Z.: Granular representation of data: a design of families of \(\epsilon \)-information granules. IEEE Trans. Fuzzy Syst. 26(4), 2107–2119 (2018). ISSN 10636706.  https://doi.org/10.1109/TFUZZ.2017.2763122
  36. 36.
    Zhuang, Y.-t., et al.: Challenges and opportunities: from big data to knowledge in AI 2.0. Front. Inf. Technol. Electron. Eng. 18(1), 3–14 (2017). ISSN 2095-9184.  https://doi.org/10.1631/FITEE.1601883CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Raúl Navarro-Almanza
    • 1
    Email author
  • Juan R. Castro
    • 1
  • Mauricio A. Sanchez
    • 1
  1. 1.Universidad Autónoma de Baja CaliforniaTijuanaMexico

Personalised recommendations