Towards a rigorous science of interpretable machine learning F Doshi-Velez, B Kim arXiv preprint arXiv:1702.08608, 2017 | 801 | 2017 |

Comorbidity clusters in autism spectrum disorders: an electronic health record time-series analysis F Doshi-Velez, Y Ge, I Kohane Pediatrics 133 (1), e54-e63, 2014 | 271 | 2014 |

Unfolding physiological state: Mortality modelling in intensive care units M Ghassemi, T Naumann, F Doshi-Velez, N Brimmer, R Joshi, ... Proceedings of the 20th ACM SIGKDD international conference on Knowledge …, 2014 | 184 | 2014 |

Improving the adversarial robustness and interpretability of deep neural networks by regularizing their input gradients AS Ross, F Doshi-Velez arXiv preprint arXiv:1711.09404, 2017 | 178 | 2017 |

Variational inference for the Indian buffet process F Doshi, K Miller, J Van Gael, YW Teh Artificial Intelligence and Statistics, 137-144, 2009 | 160 | 2009 |

Right for the right reasons: Training differentiable models by constraining their explanations AS Ross, MC Hughes, F Doshi-Velez arXiv preprint arXiv:1703.03717, 2017 | 149 | 2017 |

A Bayesian nonparametric approach to modeling motion patterns J Joseph, F Doshi-Velez, AS Huang, N Roy Autonomous Robots 31 (4), 383, 2011 | 142 | 2011 |

A Bayesian nonparametric approach to modeling motion patterns J Joseph, F Doshi-Velez, AS Huang, N Roy Autonomous Robots 31 (4), 383, 2011 | 142 | 2011 |

Accountability of AI under the law: The role of explanation F Doshi-Velez, M Kortz, R Budish, C Bavitz, S Gershman, D O'Brien, ... arXiv preprint arXiv:1711.01134, 2017 | 124 | 2017 |

The variational Gaussian process D Tran, R Ranganath, DM Blei arXiv preprint arXiv:1511.06499, 2015 | 116 | 2015 |

The infinite partially observable Markov decision process F Doshi-Velez Advances in neural information processing systems, 477-485, 2009 | 111 | 2009 |

The infinite partially observable Markov decision process F Doshi-Velez Advances in neural information processing systems, 477-485, 2009 | 111 | 2009 |

A bayesian framework for learning rule sets for interpretable classification T Wang, C Rudin, F Doshi-Velez, Y Liu, E Klampfl, P MacNeille The Journal of Machine Learning Research 18 (1), 2357-2393, 2017 | 100 | 2017 |

Learning and policy search in stochastic dynamical systems with bayesian neural networks S Depeweg, JM Hernández-Lobato, F Doshi-Velez, S Udluft arXiv preprint arXiv:1605.07127, 2016 | 97 | 2016 |

Beyond sparsity: Tree regularization of deep models for interpretability M Wu, MC Hughes, S Parbhoo, M Zazzi, V Roth, F Doshi-Velez arXiv preprint arXiv:1711.06178, 2017 | 87 | 2017 |

How do humans understand explanations from machine learning systems? an evaluation of the human-interpretability of explanation M Narayanan, E Chen, J He, B Kim, S Gershman, F Doshi-Velez arXiv preprint arXiv:1802.00682, 2018 | 82 | 2018 |

Reinforcement learning with limited reinforcement: Using Bayes risk for active learning in POMDPs F Doshi, J Pineau, N Roy Proceedings of the 25th international conference on Machine learning, 256-263, 2008 | 81 | 2008 |

Efficient model learning for dialog management F Doshi, N Roy Proceedings of the ACM/IEEE international conference on Human-robot …, 2007 | 78 | 2007 |

A roadmap for a rigorous science of interpretability F Doshi-Velez, B Kim arXiv preprint arXiv:1702.08608 2, 2017 | 77 | 2017 |

Spoken language interaction with model uncertainty: an adaptive human–robot interaction system F Doshi, N Roy Connection Science 20 (4), 299-318, 2008 | 76 | 2008 |