nach oben

Erschienen in:

2018 | OriginalPaper | Buchkapitel

Modelling Machine Learning Models

verfasst von : Raül Fabra-Boluda, Cèsar Ferri, José Hernández-Orallo, Fernando Martínez-Plumed, M. José Ramírez-Quintana

Erschienen in: Philosophy and Theory of Artificial Intelligence 2017

Verlag: Springer International Publishing

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Machine learning (ML) models make decisions for governments, companies, and individuals. Accordingly, there is the increasing concern of not having a rich explanatory and predictive account of the behaviour of these ML models relative to the users’ interests (goals) and (pre-)conceptions (ontologies). We argue that the recent research trends in finding better characterisations of what a ML model does are leading to the view of ML models as complex behavioural systems. A good explanation for a model should depend on how well it describes the behaviour of the model in simpler, more comprehensible, or more understandable terms according to a given context. Consequently, we claim that a more contextual abstraction is necessary (as is done in system theory and psychology), which is very much like building a subjective mind modelling problem. We bring some research evidence of how this partial and subjective modelling of machine learning models can take place, suggesting that more machine learning is the answer.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Vorheriges Kapitel Where Intelligence Lies: Externalist and Sociolinguistic Perspectives on the Turing Test and AI

Nächstes Kapitel Is Programming Done by Projection and Introspection?

Balasubramanian, V., Ho, S.-S., Vovk, V.: Conformal Prediction for Reliable Machine Learning: Theory, Adaptations and Applications. Newnes, Oxford (2014)MATH

Bella, A., Ferri, C., Hernández-Orallo, J., Ramírez-Quintana, M.J.: Using negotiable features for prescription problems. Computing 91(2), 135–168 (2011)CrossRef

Bella, A., Ferri, C., Hernández-Orallo, J., Ramírez-Quintana, M.J.: On the effect of calibration in classifier combination. Appl. Intell. 38(4), 566–585 (2013)CrossRef

Blanco-Vega, R., Ferri-Ramírez, C., Hernández-Orallo, J., Ramírez-Quintana, M.: Estimating the class probability threshold without training data. In: Workshop on ROC Analysis in Machine Learning, p. 9 (2006)

Blanco-Vega, R., Hernández-Orallo, J., Ramírez-Quintana, M.: Analysing the trade-off between comprehensibility and accuracy in mimetic models. In: Discovery Science, pp. 35–39 (2004)

Boden, M.A.: Computer Models of Mind: Computational Approaches in Theoretical Psychology. Cambridge University Press, New York (1988)

Chart, D.: A Theory of Understanding: Philosophical and Psychological Perspectives. Routledge, New York (2000)

Core, M., Lane, H.C., van Lent, M., Gomboc, D., Solomon, S., Rosenberg, M.: Building explainable artificial intelligence systems. In: Proceedings of the 18th Innovative Applications of Artificial Intelligence Conference (2006)

Cousot, P., Cousot, R.: Abstract interpretation: a unified lattice model for static analysis of programs by construction or approximation of fixpoints. In: Proceedings of the 4th ACM SIGACT-SIGPLAN Symposium on Principles of Programming Languages, pp. 238–252 (1977)

Cui, Z., Chen, W., He, Y., Chen, Y.: Optimal action extraction for random forests and boosted trees. In: Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 179–188 (2015)

Domingos, P.: Knowledge discovery via multiple models. Intell. Data Anal. 2(1–4), 187–202 (1998)CrossRef

Doshi-Velez, F., Kim, B.: Towards a rigorous science of interpretable machine learning. arXiv (2017)

Elkan, C.: The foundations of cost-sensitive learning. In: International Joint Conference on Artificial Intelligence, vol. 17, pp. 973–978 (2001)

Fenton, N.E., Neil, M.: Software metrics: successes, failures and new directions. J. Syst. Softw. 47(2), 149–157 (1999)CrossRef

Ferri, C., Hernández-Orallo, J., Ramírez-Quintana, M.J.: From ensemble methods to comprehensible models. In: 5th International Conference on Discovery Science, pp. 165–177 (2002)

Ferri, C., Hernández-Orallo, J., Martínez-Usó, A., Ramírez-Quintana, M.: Identifying dominant models when the noise context is known. In: First Workshop on Generalization and Reuse of Machine Learning Models Over Multiple Contexts (2014)

Ferri, C., Hernández-Orallo, J., Modroiu, R.: An experimental comparison of performance measures for classification. Pattern Recogn. Lett. 30(1), 27–38 (2009)CrossRef

Hernández-Orallo, J., Flach, P.A., Ferri, C.: A unified view of performance metrics: translating threshold choice into expected classification loss. J. Mach. Learn. Res. 13, 2813–2869 (2012)MathSciNetMATH

Hernández-Orallo, J.: The Measure of All Minds: Evaluating Natural and Artificial Intelligence. Cambridge University Press, New York (2017)CrossRef

Hernández-Orallo, J., Martínez-Usó, A., Prudêncio, R.B., Kull, M., Flach, P., Farhan Ahmed, C., Lachiche, N.: Reframing in context: a systematic approach for model reuse in machine learning. AI Commun. 29(5), 551–566 (2016)MathSciNetCrossRef

Huang, L., Joseph, A.D., Nelson, B., Rubinstein, B.I., Tygar, J.D.: Adversarial machine learning. In: Proceedings of the 4th ACM Workshop on Security and Artificial Intelligence, pp. 43–58 (2011)

Jain, S., Osherson, D., Royer, J.S., Sharma, A.: Systems that Learn, 2nd edn. MIT Press, Cambridge (1999)

Japkowicz, N., Shah, M.: Evaluating Learning Algorithms: A Classification Perspective. Cambridge University Press, New York (2011)CrossRef

Kamiran, F., Calders, T.: Classifying without discriminating. In: 2nd International Conference on Computer, Control and Communication, pp. 1–6 (2009)

Langley, P., et al.: Selection of relevant features in machine learning. In: Proceedings of the AAAI Fall Symposium on Relevance, vol. 184, pp. 245–271 (1994)

Lichman, M.: UCI machine learning repository (2013)

Lyu, Q., Chen, Y., Li, Z., Cui, Z., Chen, L., Zhang, X., Shen, H.: Extracting actionability from machine learning models by sub-optimal deterministic planning. arXiv preprint arXiv:1611.00873 (2016)

Martínez-Plumed, F., Prudêncio, R.B.C., Usó, A.M., Hernández-Orallo, J.: Making sense of item response theory in machine learning. In: European Conference on Artificial Intelligence, pp. 1140–1148 (2016)

Ribeiro, M.T., Singh, S., Guestrin, C.: Why should I trust you?: Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144 (2016)

Samek, W., Wiegand, T., Müller, K.-R.: Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models, ArXiv e-prints (2017)

Tickle, A.B., Andrews, R., Golea, M., Diederich, J.: The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks. Trans. Neur. Netw. 9(6), 1057–1068 (1998)CrossRef

Turney, P.D.: The management of context-sensitive features: a review of strategies. arXiv preprint cs/0212037 (2002)

Weller, A.: Challenges for transparency. arXiv preprint arXiv:1708.01870 (2017)

Yang, Q., Yin, J., Ling, C., Pan, R.: Extracting actionable knowledge from decision trees. IEEE Trans. Knowl. Data Eng. 19(1), 43–56 (2007)CrossRef

Titel: Modelling Machine Learning Models
verfasst von: Raül Fabra-Boluda
Cèsar Ferri
José Hernández-Orallo
Fernando Martínez-Plumed
M. José Ramírez-Quintana
Verlag: Springer International Publishing
Buch: Philosophy and Theory of Artificial Intelligence 2017
Print ISBN: 978-3-319-96447-8

Electronic ISBN: 978-3-319-96448-5

Copyright-Jahr: 2018
DOI: https://doi.org/10.1007/978-3-319-96448-5_16

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"