| Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations AS Ross, MC Hughes, F Doshi-Velez International Joint Conference on Artificial Intelligence, 2017 | 370 | 2017 |
| Beyond sparsity: Tree regularization of deep models for interpretability M Wu, MC Hughes, S Parbhoo, M Zazzi, V Roth, F Doshi-Velez Thirty-Second AAAI Conference on Artificial Intelligence, 2018 | 183 | 2018 |
| Memoized Online Variational Inference for Dirichlet Process Mixture Models MC Hughes, EB Sudderth Advances in Neural Information Processing Systems, 1133-1141, 2013 | 111 | 2013 |
| Joint modeling of multiple time series via the beta process with application to motion capture segmentation EB Fox, MC Hughes, EB Sudderth, MI Jordan The Annals of Applied Statistics 8 (3), 1281-1313, 2014 | 107 | 2014 |
| Feature Robustness in Non-stationary Health Records: Caveats to Deployable Model Performance in Common Clinical Machine Learning Tasks B Nestor, M McDermott, W Boag, G Berner, T Naumann, MC Hughes, ... Proceedings of the 4th Machine Learning for Healthcare Conference, 2019 | 65 | 2019 |
| MIMIC-Extract: A data extraction, preprocessing, and representation pipeline for MIMIC-III S Wang, MBA McDermott, G Chauhan, M Ghassemi, MC Hughes, ... Proceedings of the ACM Conference on Health, Inference, and Learning, 222-235, 2020 | 61 | 2020 |
| Predicting intervention onset in the ICU with switching state space models M Ghassemi, M Wu, MC Hughes, P Szolovits, F Doshi-Velez AMIA Summits on Translational Science Proceedings 2017, 82, 2017 | 49 | 2017 |
| Effective split-merge monte carlo methods for nonparametric models of sequential data MC Hughes, EB Fox, EB Sudderth Advances in Neural Information Processing Systems, 1295-1303, 2012 | 49 | 2012 |
| Reliable and Scalable Variational Inference for the Hierarchical Dirichlet Process. MC Hughes, DI Kim, EB Sudderth AISTATS, 2015 | 43 | 2015 |
| The Nonparametric Metadata Dependent Relational Model DI Kim, MC Hughes, EB Sudderth The 29th International Conference on Machine Learning (ICML 2012), 2012 | 29 | 2012 |
| Semi-Supervised Prediction-Constrained Topic Models MC Hughes, G Hope, L Weiner, TH McCoy Jr, RH Perlis, E Sudderth, ... International Conference on Artificial Intelligence and Statistics, 1067-1076, 2018 | 28 | 2018 |
| Scalable Adaptation of State Complexity for Nonparametric Hidden Markov Models MC Hughes, WT Stephenson, EB Sudderth Advances in Neural Information Processing Systems, 2015 | 24 | 2015 |
| POPCORN: Partially Observed Prediction COnstrained ReiNforcement Learning J Futoma, MC Hughes, F Doshi-Velez The 23rd International Conference on Artificial Intelligence and Statistics …, 2020 | 23 | 2020 |
| Rethinking clinical prediction: Why machine learning must consider year of care and feature aggregation B Nestor, M McDermott, G Chauhan, T Naumann, MC Hughes, ... arXiv preprint arXiv:1811.12583, 2018 | 20 | 2018 |
| Bnpy: Reliable and scalable variational inference for Bayesian nonparametric models MC Hughes, EB Sudderth NIPS Probabilistic Programimming Workshop, 2014 | 18 | 2014 |
| Nonparametric Discovery of Activity Patterns from Video Collections MC Hughes, EB Sudderth The Eighth IEEE Computer Society Workshop on Perceptual Organization in …, 2012 | 18 | 2012 |
| The role of machine learning in clinical research: transforming the future of evidence generation EH Weissler, T Naumann, T Andersson, R Ranganath, O Elemento, Y Luo, ... Trials, 2021 | 16 | 2021 |
| Fast Learning of Clusters and Topics via Sparse Posteriors MC Hughes, EB Sudderth arXiv preprint arXiv:1609.07521, 2016 | 13 | 2016 |
| Predicting treatment dropout after antidepressant initiation MF Pradier, TH McCoy Jr, M Hughes, RH Perlis, F Doshi-Velez Translational Psychiatry 10 (1), 1-8, 2020 | 12 | 2020 |
| Regional tree regularization for interpretability in deep neural networks M Wu, S Parbhoo, M Hughes, R Kindle, L Celi, M Zazzi, V Roth, ... Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 6413-6421, 2020 | 10 | 2020 |
Finale Doshi-VelezProfessor, HarvardVerified email at seas.harvard.edu
