Sotabase

Career

· John L. Loeb Professor of Engineering and Applied Sciences, Harvard University2014–
· Postdoctoral Fellow in Bioinformatics, Harvard Medical School2007–2009
· Master's Degree, Trinity College, Cambridge2007–2009
· Doctor of Philosophy, Computer Science, Massachusetts Institute of Technology2005–2012
· Master's Degree, Massachusetts Institute of Technology2005–2007
· Bachelor of Science, Aerospace Engineering and Physics, Massachusetts Institute of Technology2001–2005
· Postgraduate Student, Massachusetts Institute of Technology

Publications (273)

Towards A Rigorous Science of Interpretable Machine Learning
2017
4,603
cited
Do no harm: a roadmap for responsible machine learning for health care
Nature Medicine · 2019
748
cited
Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
AAAI Conference on Artificial Intelligence · 2017
724
cited
Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations
International Joint Conference on Artificial Intelligence · 2017
643
cited
Accountability of AI Under the Law: The Role of Explanation
arXiv.org · 2017
473
cited
Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
International Conference on Machine Learning · 2017
461
cited
Comorbidity Clusters in Autism Spectrum Disorders: An Electronic Health Record Time-Series Analysis
Pediatrics · 2014
395
cited
Guidelines for reinforcement learning in healthcare
Nature Medicine · 2019
388
cited
The myth of generalisability in clinical research and machine learning in health care
The Lancet Digital Health · 2020
329
cited
Beyond Sparsity: Tree Regularization of Deep Models for Interpretability
AAAI Conference on Artificial Intelligence · 2017
293
cited
How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation
arXiv.org · 2018
260
cited
A Bayesian Framework for Learning Rule Sets for Interpretable Classification
Journal of machine learning research · 2017
251
cited
How machine-learning recommendations influence clinician treatment selections: the example of antidepressant selection
Translational Psychiatry · 2021
242
cited
Unfolding physiological state: mortality modelling in intensive care units
Knowledge Discovery and Data Mining · 2014
230
cited
Explainable Reinforcement Learning via Reward Decomposition
2019
223
cited
Considerations for Evaluation and Generalization in Interpretable Machine Learning
2018
176
cited
An Evaluation of the Human-Interpretability of Explanation
arXiv.org · 2019
175
cited
Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks
International Conference on Learning Representations · 2016
163
cited
Designing AI for Trust and Collaboration in Time-Constrained Medical Decisions: A Sociotechnical Lens
International Conference on Human Factors in Computing Systems · 2021
162
cited
A Bayesian nonparametric approach to modeling motion patterns
Auton. Robots · 2011
160
cited
Sotabase
Finale Doshi-Velez | Researcher Profile | Sotabase | Sotabase