Zachary C. Lipton
Skip Abstract Section
Abstract
In machine learning, the concept of interpretability is both important and slippery.
- Athey, S. and Imbens, G.W. Machine-learning methodsm 2015; https://arxiv.org/abs/1504.01132v1.Google Scholar
- Caruana, R., Kangarloo, H., Dionisio, J. D, Sinha, U. and Johnson, D. Case-based explanation of non-case-based learning methods. In Proceedings of the Amer. Med. Info. Assoc. Symp., 1999, 12--215.Google Scholar
- Caruana, R., Lou, Y., Gehrke, J., Koch, P., Sturm, M. and Elhadad, N. Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission. In Proceedings of the 21<sup>st</sup> SIGKDD Intern. Conf. Knowledge Discovery and Data Mining, 2017, 1721--1730. Google ScholarDigital Library
- Chang, J., Gerrish, S., Wang, C., Boyd-Graber, J.L., Blei, D.M. 2009. Reading tea leaves: how humans interpret topic models. In Proceedings of the 22<sup>nd</sup> Intern. Conf. Neural Information Processing Systems, 2009, 288--296. Google ScholarDigital Library
- Doshi-Velez, F., Wallace, B. and Adams, R. Graph-sparse lDA: A topic model with structured sparsity. In Proceedings of the 29<sup>th</sup> Assoc. Advance. Artificial Intelligence Conf., 2015, 2575--2581. Google ScholarDigital Library
- Fair Isaac Corporation (FICO). Introduction to model builder scorecard, 2011; http://www.fico.com/en/latest-thinking/white-papers/introduction-to-model-builder-scorecard.Google Scholar
- Goodman, B. and Flaxman, S. European Union regulations on algorithmic decision-making and a 'right to explanation,' 2016; https://arxiv.org/abs/1606.08813v3.Google Scholar
- Huysmans, J., Dejaeger, K., Mues, C., Vanthienen, J. and Baesens, B. An empirical evaluation of the comprehensibility of decision table, tree- and rule-based predictive models. J. Decision Support Systems 51, 1 (2011), 141--154. Google ScholarDigital Library
- Kim, B. Interactive and interpretable machine-learning models for human-machine collaboration. Ph.D. thesis. Massachusetts Institute of Technology, Cambridge, MA, 2015.Google Scholar
- Kim, B., Rudin, C. and Shah, J.A. The Bayesian case model: A generative approach for case-based reasoning and prototype classification. In Proceedings of the 27<sup>th</sup> Intern. Conf. Neural Information Processing Systems, Vol. 2, 1952--1960, 2014. Google ScholarDigital Library
- Kim, B., Glassman, E., Johnson, B. and Shah, J. iBCM: Interactive Bayesian case model empowering humans via intuitive interaction. Massachusetts Institute of Technology, Cambridge, MA, 2015.Google Scholar
- Krening, S., Harrison, B., Feigh, K., Isbell, C., Riedl, M. and Thomaz, A. Learning from explanations using sentiment and advice in RL. IEEE Trans. Cognitive and Developmental Systems 9, 1 (2017), 41--55.Google Scholar
- Lipton, Z.C., Kale, D.C. and Wetzel, R. Modeling missing data in clinical time series with RNNs. In Proceedings of Machine Learning for Healthcare, 2016.Google Scholar
- Liu, C., Rani, P. and Sarkar, N. 2006. An empirical study of machine-learning techniques for affect recognition in human-robot interaction. Pattern Analysis and Applications 9, 1 (2006), 58--69. Google ScholarDigital Library
- Lou, Y., Caruana, R. and Gehrke, J. Intelligible models for classification and regression. In Proceedings of the 18<sup>th</sup> ACM SIGKDD Intern. Conf. Knowledge Discovery and Data Mining, 2012, 150--158. Google ScholarDigital Library
- Lou, Y., Caruana, R., Gehrke, J. and Hooker, G. Accurate intelligible models with pairwise interactions. In Proceedings of the 19<sup>th</sup> ACM SIGKDD Intern. Conf. Knowledge Discovery and Data Mining, 2013, 623--631. Google ScholarDigital Library
- Mahendran, A. and Vedaldi, A. Understanding deep image representations by inverting them. In Proceedings of the IEEE Conf. Computer Vision and Pattern Recognition, 2015, 1--9.Google ScholarCross Ref
- McAuley, J. and Leskovec, J. Hidden factors and hidden topics: Understanding rating dimensions with review text. In Proceedings of the 7<sup>th</sup> ACM Conf. Recommender Systems, 2013, 165--172. Google ScholarDigital Library
- Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S. and Dean, J. Distributed representations of words and phrases and their compositionality. In Proceedings of the 26<sup>th</sup> Intern. Conf. Neural Information Processing Systems 2, 2013, 3111--3119. Google ScholarDigital Library
- Mordvintsev, A., Olah, C. and Tyka, M. Inceptionism: Going deeper into neural networks. Google AI Blog; https://ai.googleblog.com/2015/06/inceptionism-going-deeper-into-neural.html.Google Scholar
- Mounk, Y. Is Harvard unfair to Asian-Americans? New York Times (Nov. 24, 2014); http://www.nytimes.com/2014/11/25/opinion/is-harvard-unfair-to-asian-americans.html.Google Scholar
- Pearl, J. Causality. Cambridge University Press, Cambridge, MA, 2009.Google Scholar
- Ribeiro, M.T., Singh, S. and Guestrin, C. 'Why should I trust you?' Explaining the predictions of any classifier. In Proceedings of the 22<sup>nd</sup> SIGKDD Intern. Conf. Knowledge Discovery and Data Mining, 2016, 1135--1144. Google ScholarDigital Library
- Ridgeway, G., Madigan, D., Richardson, T. and O'Kane, J. Interpretable boosted naïve Bayes classification. In Proceedings of the 4<sup>th</sup> Intern. Conf. Knowledge Discovery and Data Mining, 1998, 101--104. Google ScholarDigital Library
- Simonyan, K., Vedaldi, A., Zisserman, A. Deep inside convolutional networks: Visualising image classification models and saliency maps, 2013; https://arxiv.org/abs/1312.6034.Google Scholar
- Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I. and Fergus, R. Intriguing properties of neural networks, 2013; https://arxiv.org/abs/1312.6199.Google Scholar
- Tibshirani, R. 1996. Regression shrinkage and selection via the lasso. J. Royal Statistical Society: Series B: Statistical Methodology 58, 1 (1996), 267--288.Google Scholar
- Van der Maaten, L. and Hinton, G. Visualizing data using t-SNE. J. Machine Learning Research 9 (2008), 2579--2605.Google Scholar
- Wang, H.-X., Fratiglioni, L., Frisoni, G. B., Viitanen, M. and Winblad, B. Smoking and the occurrence of Alzheimer's disease: Cross-sectional and longitudinal data in a population-based study. Amer. J. Epidemiology 149, 7 (1999), 640--644.Google ScholarCross Ref
- Wang, Z., Freitas, N. and Lanctot, M. Dueling network architectures for deep reinforcement learning. In Proceedings of the 33<sup>rd</sup> Intern. Conf. Machine Learning 48, 2016, 1995--2003. Google ScholarDigital Library
Index Terms
- The mythos of model interpretability
Recommendations
Interpretability assessment of fuzzy knowledge bases
Computing with words (CWW) relies on linguistic representation of knowledge that is processed by operating at the semantical level defined through fuzzy sets. Linguistic representation of knowledge is a major issue when fuzzy rule based models are ...
Low-level interpretability and high-level interpretability: a unified view of data-driven interpretable fuzzy system modelling
This paper aims at providing an in-depth overview of designing interpretable fuzzy inference models from data within a unified framework. The objective of complex system modelling is to develop reliable and understandable models for human being to get ...
Improving the interpretability of classification rules discovered by an ant colony algorithm
GECCO '13: Proceedings of the 15th annual conference on Genetic and evolutionary computationThe vast majority of Ant Colony Optimization (ACO) algorithms for inducing classification rules use an ACO-based procedure to create a rule in an one-at-a-time fashion. An improved search strategy has been proposed in the cAnt-MinerPB algorithm, where ...
Comments