Paving the Way to Explainable Artificial Intelligence with Fuzzy Modeling | SpringerLink
Skip to main content
Springer Nature Link
Log in

Paving the Way to Explainable Artificial Intelligence with Fuzzy Modeling

Tutorial

  • Conference paper
  • First Online:
Fuzzy Logic and Applications (WILF 2018)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 11291))

Included in the following conference series:

Abstract

Explainable Artificial Intelligence (XAI) is a relatively new approach to AI with special emphasis to the ability of machines to give sound motivations about their decisions and behavior. Since XAI is human-centered, it has tight connections with Granular Computing (GrC) in general, and Fuzzy Modeling (FM) in particular. However, although FM has been originally conceived to provide easily understandable models to users, this property cannot be taken for grant but it requires careful design choices. Furthermore, full integration of FM into XAI requires further processing, such as Natural Language Generation (NLG), which is a matter of current research.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 5719
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 7149
Price includes VAT (Japan)
  • 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

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    The full history has been reported by The New York Times, on May 2, 2017, p. A22. See https://nyti.ms/2qoe8FC.

  2. 2.

    https://www.acm.org/binaries/content/assets/public-policy/2017_joint_statement_algorithms.pdf.

  3. 3.

    https://eur-lex.europa.eu/legal-content/EN/ALL/?uri=CELEX:32016R0679.

  4. 4.

    See note (71) in the preamble of GDPR. Actually, GDPR is quite timid in affirming the right of explanation [36], thence the need of more precise regulations on the subject in future.

  5. 5.

    https://www.darpa.mil/program/explainable-artificial-intelligence.

  6. 6.

    https://www7.inra.fr/mia/M/fispro/fispro2013_en.html.

  7. 7.

    https://sourceforge.net/projects/guajefuzzy/.

References

  1. Alcala-Fdez, J., Alonso, J.M.: A survey of fuzzy systems software: taxonomy, current research trends, and prospects. IEEE Trans. Fuzzy Syst. 24(1), 40–56 (2016). https://doi.org/10.1109/TFUZZ.2015.2426212

    Article  Google Scholar 

  2. Alonso, J.M., Magdalena, L.: Generating understandable and accurate fuzzy rule-based systems in a Java environment. In: Fanelli, A.M., Pedrycz, W., Petrosino, A. (eds.) WILF 2011. LNCS (LNAI), vol. 6857, pp. 212–219. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-23713-3_27

    Chapter  Google Scholar 

  3. Alonso, J., Conde-Clemente, P., Trivino, G.: Linguistic description of complex phenomena with the rLDCP R package. In: Proceedings of the 10th International Conference on Natural Language Generation, pp. 243–244 (2017)

    Google Scholar 

  4. Alonso, J.M., Magdalena, L.: HILK++: an interpretability-guided fuzzy modeling methodology for learning readable and comprehensible fuzzy rule-based classifiers. Soft Comput. 15(10), 1959–1980 (2011). https://doi.org/10.1007/s00500-010-0628-5

    Article  Google Scholar 

  5. Alonso, J.M., Magdalena, L., González-Rodríguez, G.: Looking for a good fuzzy system interpretability index: an experimental approach. Int. J. Approx. Reason. 51(1), 115–134 (2009). https://doi.org/10.1016/j.ijar.2009.09.004

    Article  MathSciNet  Google Scholar 

  6. Alonso, J.M., Magdalena, L., Guillaume, S.: HILK: a new methodology for designing highly interpretable linguistic knowledge bases using the fuzzy logic formalism. Int. J. Intell. Syst. 23(7), 761–794 (2008). https://doi.org/10.1002/int.20288

    Article  MATH  Google Scholar 

  7. Alonso, J.M., Castiello, C., Mencar, C.: Interpretability of fuzzy systems: current research trends and prospects. In: Kacprzyk, J., Pedrycz, W. (eds.) Springer Handbook of Computational Intelligence, pp. 219–237. Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-662-43505-2_14

    Chapter  Google Scholar 

  8. Alonso, J.M., Ramos-soto, A., Castiello, C., Mencar, C.: Hybrid data-expert explainable beer style classifier. In: IJCAI/ECAI Workshop on Explainable Artificial Intelligence (XAI 2018), pp. 1–5 (2018). https://www.dropbox.com/s/jgzkfws41ulkzxl/proceedings.pdf?dl=0

  9. Bargiela, A., Pedrycz, W.: Human-Centric Information Processing Through Granular Modelling. SCI, vol. 182. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-540-92916-1

    Book  Google Scholar 

  10. Biran, O., Cotton, C.: Explanation and justification in machine learning: a survey. In: Workshop on Explainable AI (XAI), IJCAI 2017, pp. 8–13 (2017). http://www.intelligentrobots.org/files/IJCAI2017/

  11. Bustince, H., Barrenechea, E., Fernández, J., Pagola, M., Montero, J.: The origin of fuzzy extensions. In: Kacprzyk, J., Pedrycz, W. (eds.) Springer Handbook of Computational Intelligence, pp. 89–112. Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-662-43505-2_6

    Chapter  MATH  Google Scholar 

  12. Casillas, J., Cordón, O., Triguero, F.H., Magdalena, L.: Interpretability Issues in Fuzzy Modeling, vol. 128. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-540-37057-4

    Book  Google Scholar 

  13. Castiello, C., Mencar, C., Lucarelli, M., Rothlauf, F.: Efficiency improvement of DC* through a genetic guidance. In: 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pp. 1–6. IEEE, Naples, July 2017. https://doi.org/10.1109/FUZZ-IEEE.2017.8015585

  14. Doran, D., Schulz, S., Besold, T.R.: What does explainable AI really mean? A new conceptualization of perspectives. In: Proceedings of the First International Workshop on Comprehensibility and Explanation in AI and ML 2017 co-located with 16th International Conference of the Italian Association for Artificial Intelligence (AI*IA 2017). CEUR Workshop Proceedings, vol. 2071 (2017). http://ceur-ws.org/Vol-2071/CExAIIA_2017_paper_2.pdf

  15. Fernandez, A., del Jesus, M.J., Cordon, O., Marcelloni, F., Herrera, F.: Evolutionary fuzzy systems for explainable artificial intelligence: why, when, what for, and where to? IEEE Comput. Intell. Mag., 69–81 (2019). https://doi.org/10.1109/MCI.2018.2881645

    Article  Google Scholar 

  16. Gacto, M., Alcalá, R., Herrera, F.: Interpretability of linguistic fuzzy rule-based systems: an overview of interpretability measures. Inf. Sci. 181(20), 4340–4360 (2011). https://doi.org/10.1016/J.INS.2011.02.021

    Article  Google Scholar 

  17. Gatt, A., Krahmer, E.: Survey of the state of the art in natural language generation: core tasks, applications and evaluation. J. Artif. Intell. Res. 61, 65–170 (2018). https://doi.org/10.1613/jair.5477

    Article  MathSciNet  MATH  Google Scholar 

  18. Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. 51(5), 1–42 (2018). https://doi.org/10.1145/3236009

    Article  Google Scholar 

  19. Guillaume, S., Charnomordic, B.: Learning interpretable fuzzy inference systems with FisPro. Inf. Sci. 181(20), 4409–4427 (2011). https://doi.org/10.1016/J.INS.2011.03.025

    Article  Google Scholar 

  20. John, R., Coupland, S.: Type-2 fuzzy logic: challenges and misconceptions [discussion forum]. IEEE Comput. Intell. Mag. 7(3), 48–52 (2012). https://doi.org/10.1109/MCI.2012.2200632

    Article  Google Scholar 

  21. Magdalena, L.: Do hierarchical fuzzy systems really improve interpretability? In: Medina, J., et al. (eds.) IPMU 2018. CCIS, vol. 853, pp. 16–26. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-91473-2_2

    Chapter  Google Scholar 

  22. Mamdani, E.H., Assilian, S.: An experiment in linguistic synthesis with a fuzzy logic controller. Int. J. Man-Mach. Stud. (1975). https://doi.org/10.1016/S0020-7373(75)80002-2

    Article  MATH  Google Scholar 

  23. Mencar, C., Castiello, C., Cannone, R., Fanelli, A.M.: Design of fuzzy rule-based classifiers with semantic cointension. Inf. Sci. 181(20), 4361–4377 (2011). https://doi.org/10.1016/j.ins.2011.02.014

    Article  Google Scholar 

  24. Mencar, C., Castiello, C., Cannone, R., Fanelli, A.M.: Interpretability assessment of fuzzy knowledge bases: a cointension based approach. Int. J. Approx. Reason. 52(4), 501–518 (2011). https://doi.org/10.1016/j.ijar.2010.11.007

    Article  MathSciNet  Google Scholar 

  25. Mencar, C., Fanelli, A.M.: Interpretability constraints for fuzzy information granulation. Inf. Sci. 178(24), 4585–4618 (2008). https://doi.org/10.1016/j.ins.2008.08.015

    Article  MathSciNet  Google Scholar 

  26. Mendel, J.: Fuzzy sets for words: a new beginning. In: The 12th IEEE International Conference on Fuzzy Systems, FUZZ 2003, vol. 1, pp. 37–42 (2003). https://doi.org/10.1109/FUZZ.2003.1209334

  27. Michalski, R.S.: A theory and methodology of inductive learning. Artif. Intell. 20, 111–161 (1983). https://doi.org/10.1016/0004-3702(83)90016-4

    Article  MathSciNet  Google Scholar 

  28. Minsky, M.: Society of Mind. Simon and Schuster, New York (1988)

    Book  Google Scholar 

  29. Pinker, S.: How the Mind Works, vol. 882. Wiley/Blackwell (10.1111) (1999). https://doi.org/10.1111/j.1749-6632.1999.tb08538.x

    Article  Google Scholar 

  30. Razak, T.R., Garibaldi, J.M., Wagner, C., Pourabdollah, A., Soria, D.: Interpretability indices for hierarchical fuzzy systems. In: Proceedings of IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2017) (2017). https://doi.org/10.1109/FUZZ-IEEE.2017.8015616

  31. Revell, T.: Computer says “no comment”. New Sci. 238(3173), 40–43 (2018). https://doi.org/10.1016/S0262-4079(18)30664-X

    Article  Google Scholar 

  32. Schacter, D.L., Gilbert, D.T., Wegner, D.M.: Psychology, 2nd edn. Worth, New York (2011)

    Google Scholar 

  33. Sugeno, M., Kang, G.: Structure identification of fuzzy model. Fuzzy Sets Syst. 28(1), 15–33 (1988). https://doi.org/10.1016/0165-0114(88)90113-3

    Article  MathSciNet  MATH  Google Scholar 

  34. Takagi, T., Sugeno, M.: Fuzzy identification of systems and its applications to modeling and control. IEEE Trans. Syst. Man Cybern. SMC–15(1), 116–132 (1985). https://doi.org/10.1109/TSMC.1985.6313399

    Article  MATH  Google Scholar 

  35. Trivino, G., Sugeno, M.: Towards linguistic descriptions of phenomena. Int. J. Approx. Reason. 54(1), 22–34 (2013). https://doi.org/10.1016/J.IJAR.2012.07.004

    Article  Google Scholar 

  36. Wachter, S., Mittelstadt, B., Floridi, L.: Why a right to explanation of automated decision-making does not exist in the general data protection regulation. Int. Data Priv. Law 7(2), 76–99 (2017). https://doi.org/10.1093/idpl/ipx005

    Article  Google Scholar 

  37. Wang, Y.: On cognitive informatics. Brain Mind 4(2), 151–167 (2003). https://doi.org/10.1023/A:1025401527570

    Article  Google Scholar 

  38. Yao, Y.: The rise of granular computing. J. Chongqing Univ. Posts Telecommun. Nat. Sci. Ed. 20(3), 229–308 (2008)

    Google Scholar 

  39. Yao, Y.: A triarchic theory of granular computing. Granul. Comput. 1(2), 145–157 (2016). https://doi.org/10.1007/s41066-015-0011-0

    Article  Google Scholar 

  40. Zadeh, L.A.: Information granulation and its centrality in human and machine intelligence. In: 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation, vol. 1, pp. 486–487, October 1997. https://doi.org/10.1109/ICSMC.1997.625798

  41. Zadeh, L.A.: From computing with numbers to computing with words. From manipulation of measurements to manipulation of perceptions. IEEE Trans. Circ. Syst. I: Fundam. Theory Appl. 46(1), 105–119 (1999). https://doi.org/10.1109/81.739259

    Article  MathSciNet  MATH  Google Scholar 

  42. Zadeh, L.A.: A new direction in AI: toward a computational theory of perceptions. AI Mag. 22(1), 73–84 (2001). https://doi.org/10.1609/aimag.v22i1.1545

    Article  MATH  Google Scholar 

  43. Zadeh, L.A.: Is there a need for fuzzy logic? Inf. Sci. 178(13), 2751–2779 (2008). https://doi.org/10.1016/j.ins.2008.02.012

    Article  MathSciNet  MATH  Google Scholar 

  44. Zadeh, L.A.: Toward a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic. Fuzzy Sets Syst. 90(2), 111–127 (1997). https://doi.org/10.1016/S0165-0114(97)00077-8

    Article  MathSciNet  MATH  Google Scholar 

  45. Zhong, N., et al.: Web intelligence meets brain informatics. In: Zhong, N., Liu, J., Yao, Y., Wu, J., Lu, S., Li, K. (eds.) WImBI 2006. LNCS (LNAI), vol. 4845, pp. 1–31. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-77028-2_1

    Chapter  Google Scholar 

Download references

Acknowledgments

Supported by the Spanish “Ministerio de Economía y Competitividad” through the Ramón y Cajal Program (RYC-2016-19802).

Author information

Authors and Affiliations

  1. Dipartimento di Informatica, Università degli Studi di Bari Aldo Moro, Bari, Italy

    Corrado Mencar

  2. Centro Singular de Investigación en Tecnoloxías da Información (CiTIUS), Universidade de Santiago de Compostela, Santiago de Compostela, Spain

    José M. Alonso

Authors
  1. Corrado Mencar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. José M. Alonso
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Corrado Mencar .

Editor information

Editors and Affiliations

  1. Széchenyi István University, Győr, Hungary

    Robert Fullér

  2. Ca’ Foscari University of Venice, Venice, Italy

    Silvio Giove

  3. University of Genoa, Genoa, Italy

    Francesco Masulli

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Mencar, C., Alonso, J.M. (2019). Paving the Way to Explainable Artificial Intelligence with Fuzzy Modeling. In: Fullér, R., Giove, S., Masulli, F. (eds) Fuzzy Logic and Applications. WILF 2018. Lecture Notes in Computer Science(), vol 11291. Springer, Cham. https://doi.org/10.1007/978-3-030-12544-8_17

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-12544-8_17

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-12543-1

  • Online ISBN: 978-3-030-12544-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics