Modelling Machine Learning Models

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.

[1]  J. Doug Tygar,et al.  Adversarial machine learning , 2019, AISec '11.

[2]  José Hernández-Orallo,et al.  Analysing the Trade-Off Between Comprehensibility and Accuracy in Mimetic Models , 2004, Discovery Science.

[3]  H. Chad Lane,et al.  Building Explainable Artificial Intelligence Systems , 2006, AAAI.

[4]  Patrick Cousot,et al.  Abstract interpretation: a unified lattice model for static analysis of programs by construction or approximation of fixpoints , 1977, POPL.

[5]  Adolfo Martínez Usó,et al.  Reframing in context: A systematic approach for model reuse in machine learning , 2016, AI Commun..

[6]  Norman E. Fenton,et al.  Software metrics: successes, failures and new directions , 1999, J. Syst. Softw..

[7]  José Hernández-Orallo,et al.  On the effect of calibration in classifier combination , 2013, Applied Intelligence.

[8]  José Hernández-Orallo,et al.  The Measure of All Minds: Evaluating Natural and Artificial Intelligence , 2017 .

[9]  Joachim Diederich,et al.  The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks , 1998, IEEE Trans. Neural Networks.

[10]  Klaus-Robert Müller,et al.  Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models , 2017, ArXiv.

[11]  Toon Calders,et al.  Classifying without discriminating , 2009, 2009 2nd International Conference on Computer, Control and Communication.

[12]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[13]  Peter D. Turney.  The Management of Context-Sensitive Features: A Review of Strategies , 2002, ArXiv.

[14]  David Chart.  A Theory of Understanding: Philosophical and Psychological Perspectives , 2000 .

[15]  Margaret A. Boden,et al.  Computer Models of Mind: Computational approaches in theoretical psychology , 1988 .

[16]  José Hernández-Orallo,et al.  An experimental comparison of performance measures for classification , 2009, Pattern Recognit. Lett..

[17]  Pedro M. Domingos.  Knowledge Discovery Via Multiple Models , 1998, Intell. Data Anal..

[18]  Vladimir Vovk,et al.  Conformal Prediction for Reliable Machine Learning: Theory, Adaptations and Applications , 2014 .

[19]  Peter A. Flach,et al.  A Unified View of Performance Metrics: Translating Threshold Choice into Expected Classification Loss C` Esar Ferri , 2012 .

[20]  P. Langley.  Selection of Relevant Features in Machine Learning , 1994 .

[21]  Qiang Yang,et al.  Extracting Actionable Knowledge from Decision Trees , 2007 .

[22]  José Hernández-Orallo,et al.  Using negotiable features for prescription problems , 2011, Computing.

[23]  José Hernández-Orallo,et al.  Estimating the Class Probability Threshold without Training Data , 2006 .

[24]  José Hernández-Orallo,et al.  From Ensemble Methods to Comprehensible Models , 2002, Discovery Science.

[25]  Mohak Shah,et al.  Evaluating Learning Algorithms: A Classification Perspective , 2011 .

[26]  Adolfo Martínez Usó,et al.  Making Sense of Item Response Theory in Machine Learning , 2016, ECAI.

[27]  Been Kim,et al.  Towards A Rigorous Science of Interpretable Machine Learning , 2017, 1702.08608.

[28]  Charles Elkan,et al.  The Foundations of Cost-Sensitive Learning , 2001, IJCAI.

[29]  Yixin Chen,et al.  Optimal Action Extraction for Random Forests and Boosted Trees , 2015, KDD.