Finale Doshi-Vele

Professor at Computer Science, Harvard University0 Followers

Focused on global perspectives in artificial intelligence and machine learning, Finale Doshi-Velez serves as a Gordon McKay Professor of Computer Science at Harvard John A. Paulson School of Engineering and Applied Sciences. Her work is at the intersection of AI safety, causality, and machine learning, where she explores the implications and applications of these technologies in diverse contexts. Professor Doshi-Velez's research interests include AI safety, causality, and machine learning, with a particular emphasis on ensuring that AI systems are reliable and trustworthy. She is deeply involved in projects such as Bias2, Causal Inference, SPUDS, and Trust In Science, which aim to address the challenges and opportunities presented by AI in modern society. Her contributions to the field are recognized both within academia and industry, where she collaborates with interdisciplinary teams to push the boundaries of what AI can achieve. In addition to her research, Finale is committed to education and mentorship, guiding the next generation of computer scientists and engineers. Her teaching philosophy emphasizes critical thinking and ethical considerations in technology development, preparing students to tackle the complex challenges of the future. Through her work, she continues to shape the discourse on AI and its role in shaping a sustainable and equitable world.

Research Interests

AI safety causality machine learning bias2 causal inference SPUDS trust in science

Publications

1 - Generating interpretable predictions about antidepressant treatment stability using supervised topic models,

Michael C. Hughes , Melanie F. Pradier , Andrew Slavin Ross , Thomas H. McCoy , Roy H. Perlis , Finale Doshi-Velez ,

, 2020-03-20

2 - Heterogeneity in Antidepressant Treatment and Major Depressive Disorder Outcomes Among Clinicians,JAMA Psychiatry

Sarah Rathnam , Kamber L. Hart , Abhishek Sharma , Pilar F. Verhaak , Thomas H. McCoy , Finale Doshi-Velez , Roy H. Perlis ,

, 1003, 2024-10-01

3 - Generalization in Clinical Prediction Models: The Blessing and Curse of Measurement Indicator Variables,Critical Care Explorations

Joseph Futoma , Morgan Simons , Finale Doshi-Velez , Rishikesan Kamaleswaran ,

, e0453, 2021-06-25

4 - Comorbidity Clusters in Autism Spectrum Disorders: An Electronic Health Record Time-Series Analysis,Pediatrics

Finale Doshi-Velez , Yaorong Ge , Isaac Kohane ,

, e54-e63, 2014-01-01

5 - Predicting treatment dropout after antidepressant initiation,Translational Psychiatry

Melanie F. Pradier , Thomas H. McCoy Jr , Michael Hughes , Roy H. Perlis , Finale Doshi-Velez ,

, 2020-02-06

6 - 1185-P: Predictive Model for Hyperglycemic Events after High Dose Corticosteroid Administration,Diabetes

MORGAN G. SIMONS , JOSEPH D. FUTOMA , MICHAEL GAO , KRISTIN COREY , MARK SENDAK , KRISTA B. WHALEN , FINALE DOSHI-VELEZ , ANN S. MCGEE , TRACY SETJI ,

, 2019-06-01

7 - Understanding vasopressor intervention and weaning: risk prediction in a public heterogeneous clinical time series database,Journal of the American Medical Informatics Association

Mike Wu , Marzyeh Ghassemi , Mengling Feng , Leo A Celi , Peter Szolovits , Finale Doshi-Velez ,

, 488-495, 2016-10-05

8 - An interpretable RL framework for pre-deployment modeling in ICU hypotension management,npj Digital Medicine

Kristine Zhang , Henry Wang , Jianzhun Du , Brian Chu , Aldo Robles Arévalo , Ryan Kindle , Leo Anthony Celi , Finale Doshi-Velez ,

, 2022-11-18

9 - Optimizing for Interpretability in Deep Neural Networks with Tree Regularization,Journal of Artificial Intelligence Research

Mike Wu , Sonali Parbhoo , Michael C. Hughes , Volker Roth , Finale Doshi-Velez ,

, 1-37, 2021-09-14

10 - How machine-learning recommendations influence clinician treatment selections: the example of antidepressant selection,Translational Psychiatry

Maia Jacobs , Melanie F. Pradier , Thomas H. McCoy , Roy H. Perlis , Finale Doshi-Velez , Krzysztof Z. Gajos ,

, 2021-02-04

11 - Reward Design for an Online Reinforcement Learning Algorithm Supporting Oral Self-Care,Proceedings of the AAAI Conference on Artificial Intelligence

Anna L. Trella , Kelly W. Zhang , Inbal Nahum-Shani , Vivek Shetty , Finale Doshi-Velez , Susan A. Murphy ,

, 15724-15730, 2023-06-26

12 - Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI,Proceedings of the AAAI Conference on Human Computation and Crowdsourcing

Q. Vera Liao , Yunfeng Zhang , Ronny Luss , Finale Doshi-Velez , Amit Dhurandhar ,

, 147-159, 2022-10-14

13 - Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing Their Input Gradients,Proceedings of the AAAI Conference on Artificial Intelligence

Andrew Ross , Finale Doshi-Velez ,

, 2018-04-25

14 - “If it didn’t happen, why would I change my decision?”: How Judges Respond to Counterfactual Explanations for the Public Safety Assessment,Proceedings of the AAAI Conference on Human Computation and Crowdsourcing

Yaniv Yacoby , Ben Green , Christopher L. Griffin Jr. , Finale Doshi-Velez ,

, 219-230, 2022-10-14

15 - Designing Reinforcement Learning Algorithms for Digital Interventions: Pre-implementation Guidelines,

Anna L. Trella , Kelly W. Zhang , Inbal Nahum-Shani , Vivek Shetty , Finale Doshi-Velez , Susan A. Murphy ,

, 2022-06-02

16 - Exploring Computational User Models for Agent Policy Summarization,Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence

Isaac Lage , Daphna Lifschitz , Finale Doshi-Velez , Ofra Amir ,

, 1401-1407, 2019-08-01

Share Finale's Profile