Google
Google Scholar
Semantic Scholar
MS Academic
CiteSeerX
ORCIDFinale Doshi-Velez
Finale Doshi
Person information
- affiliation: MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, USA
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2021
[j17]Been Kim, Finale Doshi-Velez:
Machine Learning Techniques for Accountability. AI Mag. 42(1): 47-52 (2021)- [j16]Lifeng Jin, Lane Schwartz, Finale Doshi-Velez, Timothy A. Miller, William Schuler:
Depth-Bounded Statistical PCFG Induction as a Model of Human Grammar Acquisition. Comput. Linguistics 47(1): 181-216 (2021) - [c67]Andrew Slavin Ross, Nina Chen, Elisa Zhao Hang, Elena L. Glassman, Finale Doshi-Velez:
Evaluating the Interpretability of Generative Models by Interactive Reconstruction. CHI 2021: 80:1-80:15 - [c66]Maia Jacobs, Jeffrey He, Melanie F. Pradier, Barbara Lam, Andrew C. Ahn, Thomas H. McCoy, Roy H. Perlis, Finale Doshi-Velez, Krzysztof Z. Gajos:
Designing AI for Trust and Collaboration in Time-Constrained Medical Decisions: A Sociotechnical Lens. CHI 2021: 659:1-659:14 - [i70]Kristine Zhang, Yuanheng Wang, Jianzhun Du, Brian Chu, Leo Anthony Celi, Ryan Kindle, Finale Doshi-Velez:
Identifying Decision Points for Safe and Interpretable Reinforcement Learning in Hypotension Treatment. CoRR abs/2101.03309 (2021) - [i69]Melanie F. Pradier, Javier Zazo, Sonali Parbhoo, Roy H. Perlis, Maurizio Zazzi, Finale Doshi-Velez:
Preferential Mixture-of-Experts: Interpretable Models that Rely on Human Expertise as much as Possible. CoRR abs/2101.05360 (2021) - [i68]Maia Jacobs, Jeffrey He, Melanie F. Pradier, Barbara Lam, Andrew C. Ahn, Thomas H. McCoy, Roy H. Perlis, Finale Doshi-Velez, Krzysztof Z. Gajos:
Designing AI for Trust and Collaboration in Time-Constrained Medical Decisions: A Sociotechnical Lens. CoRR abs/2102.00593 (2021) - [i67]Andrew Slavin Ross, Nina Chen, Elisa Zhao Hang, Elena L. Glassman, Finale Doshi-Velez:
Evaluating the Interpretability of Generative Models by Interactive Reconstruction. CoRR abs/2102.01264 (2021) - [i66]Andrew Slavin Ross, Finale Doshi-Velez:
Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement. CoRR abs/2102.05185 (2021) - [i65]Harvineet Singh, Shalmali Joshi, Finale Doshi-Velez, Himabindu Lakkaraju:
Learning Under Adversarial and Interventional Shifts. CoRR abs/2103.15933 (2021) - [i64]Kai Wang, Sanket Shah, Haipeng Chen, Andrew Perrault, Finale Doshi-Velez, Milind Tambe:
Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning. CoRR abs/2106.03279 (2021) - [i63]Beau Coker, Weiwei Pan, Finale Doshi-Velez:
Wide Mean-Field Variational Bayesian Neural Networks Ignore the Data. CoRR abs/2106.07052 (2021) - 2020
- [c65]Andrew Slavin Ross, Weiwei Pan, Leo A. Celi, Finale Doshi-Velez:
Ensembles of Locally Independent Prediction Models. AAAI 2020: 5527-5536 - [c64]Mike Wu, Sonali Parbhoo, Michael C. Hughes, Ryan Kindle, Leo A. Celi, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez:
Regional Tree Regularization for Interpretability in Deep Neural Networks. AAAI 2020: 6413-6421 - [c63]Joseph Futoma, Michael C. Hughes, Finale Doshi-Velez:
POPCORN: Partially Observed Prediction Constrained Reinforcement Learning. AISTATS 2020: 3578-3588 - [c62]Jason Ren, Russell Kunes, Finale Doshi-Velez:
Prediction Focused Topic Models via Feature Selection. AISTATS 2020: 4420-4429 - [c61]Mingyu Lu, Zachary Shahn, Daby Sow, Finale Doshi-Velez, Li-Wei H. Lehman:
Is Deep Reinforcement Learning Ready for Practical Applications in Healthcare? A Sensitivity Analysis of Duel-DDQN for Hemodynamic Management in Sepsis Patients. AMIA 2020 - [c60]Niranjani Prasad, Barbara E. Engelhardt, Finale Doshi-Velez:
Defining admissible rewards for high-confidence policy evaluation in batch reinforcement learning. CHIL 2020: 1-9 - [c59]Omer Gottesman, Joseph Futoma, Yao Liu, Sonali Parbhoo, Leo A. Celi, Emma Brunskill, Finale Doshi-Velez:
Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions. ICML 2020: 3658-3667 - [c58]Han-Ching Ou, Kai Wang, Finale Doshi-Velez, Milind Tambe:
Active Screening on Recurrent Diseases Contact Networks with Uncertainty: A Reinforcement Learning Approach. MABS 2020: 54-65 - [c57]Sonali Parbhoo, Mario Wieser, Volker Roth, Finale Doshi-Velez:
Transfer Learning from Well-Curated to Less-Resourced Populations with HIV. MLHC 2020: 589-609 - [c56]Jianzhun Du, Joseph Futoma, Finale Doshi-Velez:
Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs. NeurIPS 2020 - [c55]Wanqian Yang, Lars Lorch, Moritz A. Graule, Himabindu Lakkaraju, Finale Doshi-Velez:
Incorporating Interpretable Output Constraints in Bayesian Neural Networks. NeurIPS 2020 - [c54]Beau Coker, Melanie Fernandes Pradier, Finale Doshi-Velez:
PoRB-Nets: Poisson Process Radial Basis Function Networks. UAI 2020: 1338-1347 - [e6]Finale Doshi-Velez, Jim Fackler, Ken Jung, David C. Kale, Rajesh Ranganath, Byron C. Wallace, Jenna Wiens:
Proceedings of the Machine Learning for Healthcare Conference, MLHC 2020, 7-8 August 2020, Virtual Event, Durham, NC, USA. Proceedings of Machine Learning Research 126, PMLR 2020 [contents] - [i62]Joseph Futoma, Muhammad A. Masood, Finale Doshi-Velez:
Identifying Distinct, Effective Treatments for Acute Hypotension with SODA-RL: Safely Optimized Diverse Accurate Reinforcement Learning. CoRR abs/2001.03224 (2020) - [i61]Joseph Futoma, Michael C. Hughes, Finale Doshi-Velez:
POPCORN: Partially Observed Prediction COnstrained ReiNforcement Learning. CoRR abs/2001.04032 (2020) - [i60]Omer Gottesman, Joseph Futoma, Yao Liu, Sonali Parbhoo, Leo Anthony Celi, Emma Brunskill, Finale Doshi-Velez:
Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions. CoRR abs/2002.03478 (2020) - [i59]Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez:
Characterizing and Avoiding Problematic Global Optima of Variational Autoencoders. CoRR abs/2003.07756 (2020) - [i58]Jiayu Yao, Emma Brunskill, Weiwei Pan, Susan Murphy, Finale Doshi-Velez:
Power-Constrained Bandits. CoRR abs/2004.06230 (2020) - [i57]Mingyu Lu, Zachary Shahn, Daby Sow, Finale Doshi-Velez, Li-Wei H. Lehman:
Is Deep Reinforcement Learning Ready for Practical Applications in Healthcare? A Sensitivity Analysis of Duel-DDQN for Sepsis Treatment. CoRR abs/2005.04301 (2020) - [i56]Yash Nair, Finale Doshi-Velez:
PAC Bounds for Imitation and Model-based Batch Learning of Contextual Markov Decision Processes. CoRR abs/2006.06352 (2020) - [i55]Sujay Thakur, Cooper Lorsung, Yaniv Yacoby, Finale Doshi-Velez, Weiwei Pan:
Learned Uncertainty-Aware (LUNA) Bases for Bayesian Regression using Multi-Headed Auxiliary Networks. CoRR abs/2006.11695 (2020) - [i54]Jianzhun Du, Joseph Futoma, Finale Doshi-Velez:
Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs. CoRR abs/2006.16210 (2020) - [i53]Théo Guénais, Dimitris Vamvourellis, Yaniv Yacoby, Finale Doshi-Velez, Weiwei Pan:
BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty. CoRR abs/2007.06096 (2020) - [i52]Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez:
Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks. CoRR abs/2007.07124 (2020) - [i51]Wanqian Yang, Lars Lorch, Moritz A. Graule, Himabindu Lakkaraju, Finale Doshi-Velez:
Incorporating Interpretable Output Constraints in Bayesian Neural Networks. CoRR abs/2010.10969 (2020) - [i50]Isaac Lage, Finale Doshi-Velez:
Learning Interpretable Concept-Based Models with Human Feedback. CoRR abs/2012.02898 (2020) - [i49]Elisa Bertino, Finale Doshi-Velez, Maria L. Gini, Daniel Lopresti, David Parkes:
Artificial Intelligence & Cooperation. CoRR abs/2012.06034 (2020)
2010 – 2019
- 2019
- [j15]Ofra Amir
, Finale Doshi-Velez, David Sarne:
Summarizing agent strategies. Auton. Agents Multi Agent Syst. 33(5): 628-644 (2019) - [j14]Muhammad A. Masood, Finale Doshi-Velez:
A Particle-Based Variational Approach to Bayesian Non-negative Matrix Factorization. J. Mach. Learn. Res. 20: 90:1-90:56 (2019) - [j13]Soumya Ghosh, Jiayu Yao, Finale Doshi-Velez:
Model Selection in Bayesian Neural Networks via Horseshoe Priors. J. Mach. Learn. Res. 20: 182:1-182:46 (2019) - [j12]Angela Fan, Finale Doshi-Velez, Luke Miratrix:
Assessing topic model relevance: Evaluation and informative priors. Stat. Anal. Data Min. 12(3): 210-222 (2019) - [c53]Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez:
Characterizing and Avoiding Problematic Global Optima of Variational Autoencoders. AABI 2019: 1-17 - [c52]Lifeng Jin, Finale Doshi-Velez, Timothy A. Miller, Lane Schwartz, William Schuler:
Unsupervised Learning of PCFGs with Normalizing Flow. ACL (1) 2019: 2442-2452 - [c51]Isaac Lage, Daphna Lifschitz, Finale Doshi-Velez, Ofra Amir:
Toward Robust Policy Summarization. AAMAS 2019: 2081-2083 - [c50]Omer Gottesman, Yao Liu, Scott Sussex, Emma Brunskill, Finale Doshi-Velez:
Combining parametric and nonparametric models for off-policy evaluation. ICML 2019: 2366-2375 - [c49]Isaac Lage, Daphna Lifschitz, Finale Doshi-Velez, Ofra Amir:
Exploring Computational User Models for Agent Policy Summarization. IJCAI 2019: 1401-1407 - [c48]Donghun Lee, Srivatsan Srinivasan, Finale Doshi-Velez:
Truly Batch Apprenticeship Learning with Deep Successor Features. IJCAI 2019: 5909-5915 - [c47]Muhammad A. Masood, Finale Doshi-Velez:
Diversity-Inducing Policy Gradient: Using Maximum Mean Discrepancy to Find a Set of Diverse Policies. IJCAI 2019: 5923-5929 - [e5]Finale Doshi-Velez, Jim Fackler, Ken Jung, David C. Kale, Rajesh Ranganath, Byron C. Wallace, Jenna Wiens:
Proceedings of the Machine Learning for Healthcare Conference, MLHC 2019, 9-10 August 2019, Ann Arbor, Michigan, USA. Proceedings of Machine Learning Research 106, PMLR 2019 [contents] - [i48]Xuefeng Peng, Yi Ding, David Wihl, Omer Gottesman, Matthieu Komorowski, Li-Wei H. Lehman, Andrew Slavin Ross, Aldo Faisal, Finale Doshi-Velez:
Improving Sepsis Treatment Strategies by Combining Deep and Kernel-Based Reinforcement Learning. CoRR abs/1901.04670 (2019) - [i47]Isaac Lage, Emily Chen, Jeffrey He, Menaka Narayanan, Been Kim, Sam Gershman, Finale Doshi-Velez:
An Evaluation of the Human-Interpretability of Explanation. CoRR abs/1902.00006 (2019) - [i46]Donghun Lee, Srivatsan Srinivasan, Finale Doshi-Velez:
Truly Batch Apprenticeship Learning with Deep Successor Features. CoRR abs/1903.10077 (2019) - [i45]Omer Gottesman, Yao Liu, Scott Sussex, Emma Brunskill, Finale Doshi-Velez:
Combining Parametric and Nonparametric Models for Off-Policy Evaluation. CoRR abs/1905.05787 (2019) - [i44]Wanqian Yang, Lars Lorch, Moritz A. Graule, Srivatsan Srinivasan, Anirudh Suresh, Jiayu Yao, Melanie F. Pradier, Finale Doshi-Velez:
Output-Constrained Bayesian Neural Networks. CoRR abs/1905.06287 (2019) - [i43]Omer Gottesman, Weiwei Pan, Finale Doshi-Velez:
A general method for regularizing tensor decomposition methods via pseudo-data. CoRR abs/1905.10424 (2019) - [i42]Niranjani Prasad, Barbara E. Engelhardt, Finale Doshi-Velez:
Defining Admissible Rewards for High Confidence Policy Evaluation. CoRR abs/1905.13167 (2019) - [i41]Isaac Lage, Daphna Lifschitz, Finale Doshi-Velez, Ofra Amir:
Exploring Computational User Models for Agent Policy Summarization. CoRR abs/1905.13271 (2019) - [i40]Muhammad A. Masood, Finale Doshi-Velez:
Diversity-Inducing Policy Gradient: Using Maximum Mean Discrepancy to Find a Set of Diverse Policies. CoRR abs/1906.00088 (2019) - [i39]Jiayu Yao, Weiwei Pan, Soumya Ghosh, Finale Doshi-Velez:
Quality of Uncertainty Quantification for Bayesian Neural Network Inference. CoRR abs/1906.09686 (2019) - [i38]Mike Wu, Sonali Parbhoo, Michael C. Hughes, Ryan Kindle, Leo A. Celi, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez:
Regional Tree Regularization for Interpretability in Black Box Models. CoRR abs/1908.04494 (2019) - [i37]Mike Wu, Sonali Parbhoo, Michael C. Hughes, Volker Roth, Finale Doshi-Velez:
Optimizing for Interpretability in Deep Neural Networks with Tree Regularization. CoRR abs/1908.05254 (2019) - [i36]Jason Ren, Russell Kunes, Finale Doshi-Velez:
Prediction Focused Topic Models via Vocab Selection. CoRR abs/1910.05495 (2019) - [i35]Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez:
Learning Deep Bayesian Latent Variable Regression Models that Generalize: When Non-identifiability is a Problem. CoRR abs/1911.00569 (2019) - [i34]Andrew Slavin Ross, Weiwei Pan, Leo Anthony Celi, Finale Doshi-Velez:
Ensembles of Locally Independent Prediction Models. CoRR abs/1911.01291 (2019) - [i33]Jason Ren, Russell Kunes, Finale Doshi-Velez:
Prediction Focused Topic Models for Electronic Health Records. CoRR abs/1911.08551 (2019) - [i32]Beau Coker, Melanie F. Pradier, Finale Doshi-Velez:
Towards Expressive Priors for Bayesian Neural Networks: Poisson Process Radial Basis Function Networks. CoRR abs/1912.05779 (2019) - 2018
- [j11]Lifeng Jin, Finale Doshi-Velez, Timothy A. Miller, William Schuler, Lane Schwartz:
Unsupervised Grammar Induction with Depth-bounded PCFG. Trans. Assoc. Comput. Linguistics 6: 211-224 (2018) - [j10]Michael Glueck, Mahdi Pakdaman Naeini, Finale Doshi-Velez, Fanny Chevalier, Azam Khan, Daniel Wigdor, Michael Brudno:
PhenoLines: Phenotype Comparison Visualizations for Disease Subtyping via Topic Models. IEEE Trans. Vis. Comput. Graph. 24(1): 371-381 (2018) - [c46]Andrew Slavin Ross, Finale Doshi-Velez:
Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing Their Input Gradients. AAAI 2018: 1660-1669 - [c45]Mike Wu, Michael C. Hughes, Sonali Parbhoo, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez:
Beyond Sparsity: Tree Regularization of Deep Models for Interpretability. AAAI 2018: 1670-1678 - [c44]Michael C. Hughes, Gabriel Hope, Leah Weiner, Thomas H. McCoy Jr., Roy H. Perlis, Erik B. Sudderth, Finale Doshi-Velez:
Semi-Supervised Prediction-Constrained Topic Models. AISTATS 2018: 1067-1076 - [c43]Omer Gottesman, Weiwei Pan, Finale Doshi-Velez:
Weighted Tensor Decomposition for Learning Latent Variables with Partial Data. AISTATS 2018: 1664-1672 - [c42]Xuefeng Peng, Yi Ding, David Wihl, Omer Gottesman, Matthieu Komorowski, Li-Wei H. Lehman, Andrew Slavin Ross, Aldo Faisal, Finale Doshi-Velez:
Improving Sepsis Treatment Strategies by Combining Deep and Kernel-Based Reinforcement Learning. AMIA 2018 - [c41]Ofra Amir, Finale Doshi-Velez, David Sarne:
Agent Strategy Summarization. AAMAS 2018: 1203-1207 - [c40]Lifeng Jin, Finale Doshi-Velez, Timothy A. Miller, William Schuler, Lane Schwartz:
Depth-bounding is effective: Improvements and Evaluation of Unsupervised PCFG Induction. EMNLP 2018: 2721-2731 - [c39]Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft:
Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning. ICML 2018: 1192-1201 - [c38]Soumya Ghosh, Jiayu Yao, Finale Doshi-Velez:
Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors. ICML 2018: 1739-1748 - [c37]Yao Liu, Omer Gottesman, Aniruddh Raghu, Matthieu Komorowski, Aldo A. Faisal, Finale Doshi-Velez, Emma Brunskill:
Representation Balancing MDPs for Off-policy Policy Evaluation. NeurIPS 2018: 2649-2658 - [c36]Isaac Lage, Andrew Slavin Ross, Samuel J. Gershman, Been Kim, Finale Doshi-Velez:
Human-in-the-Loop Interpretability Prior. NeurIPS 2018: 10180-10189 - [e4]Finale Doshi-Velez, Jim Fackler, Ken Jung, David C. Kale, Rajesh Ranganath, Byron C. Wallace, Jenna Wiens:
Proceedings of the Machine Learning for Healthcare Conference, MLHC 2018, 17-18 August 2018, Palo Alto, California. Proceedings of Machine Learning Research 85, PMLR 2018 [contents] - [i31]Menaka Narayanan, Emily Chen, Jeffrey He, Been Kim, Sam Gershman, Finale Doshi-Velez:
How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation. CoRR abs/1802.00682 (2018) - [i30]Lifeng Jin, Finale Doshi-Velez, Timothy A. Miller, William Schuler, Lane Schwartz:
Unsupervised Grammar Induction with Depth-bounded PCFG. CoRR abs/1802.08545 (2018) - [i29]Yao Liu, Omer Gottesman, Aniruddh Raghu, Matthieu Komorowski, Aldo Faisal, Finale Doshi-Velez, Emma Brunskill:
Representation Balancing MDPs for Off-Policy Policy Evaluation. CoRR abs/1805.09044 (2018) - [i28]Isaac Lage, Andrew Slavin Ross, Been Kim, Samuel J. Gershman, Finale Doshi-Velez:
Human-in-the-Loop Interpretability Prior. CoRR abs/1805.11571 (2018) - [i27]Omer Gottesman, Fredrik D. Johansson, Joshua Meier, Jack Dent, Donghun Lee, Srivatsan Srinivasan, Linying Zhang, Yi Ding, David Wihl, Xuefeng Peng, Jiayu Yao, Isaac Lage, Christopher Mosch, Li-Wei H. Lehman, Matthieu Komorowski, Aldo Faisal, Leo Anthony Celi, David A. Sontag, Finale Doshi-Velez:
Evaluating Reinforcement Learning Algorithms in Observational Health Settings. CoRR abs/1805.12298 (2018) - [i26]Soumya Ghosh, Jiayu Yao, Finale Doshi-Velez:
Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors. CoRR abs/1806.05975 (2018) - [i25]Andrew Slavin Ross, Weiwei Pan, Finale Doshi-Velez:
Learning Qualitatively Diverse and Interpretable Rules for Classification. CoRR abs/1806.08716 (2018) - [i24]Aniruddh Raghu, Omer Gottesman, Yao Liu, Matthieu Komorowski, Aldo Faisal, Finale Doshi-Velez, Emma Brunskill:
Behaviour Policy Estimation in Off-Policy Policy Evaluation: Calibration Matters. CoRR abs/1807.01066 (2018) - [i23]Lifeng Jin, Finale Doshi-Velez, Timothy A. Miller, William Schuler, Lane Schwartz:
Depth-bounding is effective: Improvements and evaluation of unsupervised PCFG induction. CoRR abs/1809.03112 (2018) - [i22]Melanie F. Pradier, Weiwei Pan, Jiayu Yao, Soumya Ghosh, Finale Doshi-Velez:
Latent Projection BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights. CoRR abs/1811.07006 (2018) - 2017
- [j9]Mike Wu, Marzyeh Ghassemi, Mengling Feng, Leo A. Celi, Peter Szolovits, Finale Doshi-Velez:
Understanding vasopressor intervention and weaning: risk prediction in a public heterogeneous clinical time series database. J. Am. Medical Informatics Assoc. 24(3): 488-495 (2017) - [j8]Tong Wang, Cynthia Rudin, Finale Doshi-Velez, Yimin Liu, Erica Klampfl, Perry MacNeille:
A Bayesian Framework for Learning Rule Sets for Interpretable Classification. J. Mach. Learn. Res. 18: 70:1-70:37 (2017) - [j7]Finale Doshi-Velez, Sinead A. Williamson:
Restricted Indian buffet processes. Stat. Comput. 27(5): 1205-1223 (2017) - [c35]Taylor W. Killian, George Dimitri Konidaris, Finale Doshi-Velez:
Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes. AAAI 2017: 4949-4950 - [c34]Marzyeh Ghassemi, Mike Wu, Michael C. Hughes, Peter Szolovits, Finale Doshi-Velez:
Predicting intervention onset in the ICU with switching state space models. CRI 2017 - [c33]Sonali Parbhoo, Jasmina Bogojeska, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez:
Combining Kernel and Model Based Learning for HIV Therapy Selection. CRI 2017 - [c32]Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft:
Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks. ICLR (Poster) 2017 - [c31]Andrew Slavin Ross, Michael C. Hughes, Finale Doshi-Velez:
Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations. IJCAI 2017: 2662-2670 - [c30]Taylor W. Killian, Samuel Daulton, Finale Doshi-Velez, George Dimitri Konidaris:
Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes. NIPS 2017: 6250-6261 - [e3]Finale Doshi-Velez, Jim Fackler, David C. Kale, Rajesh Ranganath, Byron C. Wallace, Jenna Wiens:
Proceedings of the Machine Learning for Health Care Conference, MLHC 2017, Boston, Massachusetts, USA, 18-19 August 2017. Proceedings of Machine Learning Research 68, PMLR 2017 [contents] - [i21]Angela Fan, Finale Doshi-Velez, Luke Miratrix:
Promoting Domain-Specific Terms in Topic Models with Informative Priors. CoRR abs/1701.03227 (2017) - [i20]Finale Doshi-Velez, Been Kim:
A Roadmap for a Rigorous Science of Interpretability. CoRR abs/1702.08608 (2017) - [i19]Andrew Slavin Ross, Michael C. Hughes, Finale Doshi-Velez:
Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations. CoRR abs/1703.03717 (2017) - [i18]Taylor W. Killian, Samuel Daulton, George Dimitri Konidaris, Finale Doshi-Velez:
Robust and Efficient Transfer Learning with Hidden-Parameter Markov Decision Processes. CoRR abs/1706.06544 (2017) - [i17]Michael C. Hughes, Leah Weiner, Gabriel Hope, Thomas H. McCoy Jr., Roy H. Perlis, Erik B. Sudderth, Finale Doshi-Velez:
Prediction-Constrained Training for Semi-Supervised Mixture and Topic Models. CoRR abs/1707.07341 (2017) - [i16]Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft:
Decomposition of Uncertainty for Active Learning and Reliable Reinforcement Learning in Stochastic Systems. CoRR abs/1710.07283 (2017) - [i15]Finale Doshi-Velez, Mason Kortz, Ryan Budish, Chris Bavitz, Sam Gershman, David O'Brien, Stuart Schieber, James Waldo, David Weinberger, Alexandra Wood:
Accountability of AI Under the Law: The Role of Explanation. CoRR abs/1711.01134 (2017) - [i14]Mike Wu, Michael C. Hughes, Sonali Parbhoo, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez:
Beyond Sparsity: Tree Regularization of Deep Models for Interpretability. CoRR abs/1711.06178 (2017) - [i13]Andrew Slavin Ross, Finale Doshi-Velez:
Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients. CoRR abs/1711.09404 (2017) - [i12]Michael C. Hughes, Gabriel Hope, Leah Weiner, Thomas H. McCoy Jr., Roy H. Perlis, Erik B. Sudderth, Finale Doshi-Velez:
Prediction-Constrained Topic Models for Antidepressant Recommendation. CoRR abs/1712.00499 (2017) - 2016
- [j6]Huseyin Melih Elibol, Vincent Nguyen, Scott W. Linderman, Matthew J. Johnson, Amna Hashmi, Finale Doshi-Velez:
Cross-Corpora Unsupervised Learning of Trajectories in Autism Spectrum Disorders. J. Mach. Learn. Res. 17: 133:1-133:38 (2016) - [c29]Dustin Tran, Minjae Kim, Finale Doshi-Velez:
Spectral M-estimation with Applications to Hidden Markov Models. AISTATS 2016: 1421-1430 - [c28]Cory Shain, William Bryce, Lifeng Jin, Victoria Krakovna, Finale Doshi-Velez, Timothy A. Miller, William Schuler, Lane Schwartz:
Memory-Bounded Left-Corner Unsupervised Grammar Induction on Child-Directed Input. COLING 2016: 964-975 - [c27]Tong Wang, Cynthia Rudin, Finale Doshi-Velez, Yimin Liu, Erica Klampfl, Perry MacNeille:
Bayesian Rule Sets for Interpretable Classification. ICDM 2016: 1269-1274 - [c26]Finale Doshi-Velez, George Dimitri Konidaris:
Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations. IJCAI 2016: 1432-1440 - [c25]Xide Xia, Pavlos Protopapas, Finale Doshi-Velez:
Cost-Sensitive Batch Mode Active Learning: Designing Astronomical Observation by Optimizing Telescope Time and Telescope Choice. SDM 2016: 477-485 - [e2]Finale Doshi-Velez, Jim Fackler, David C. Kale, Byron C. Wallace, Jenna Wiens:
Proceedings of the 1st Machine Learning in Health Care, MLHC 2016, Los Angeles, CA, USA, August 19-20, 2016. JMLR Workshop and Conference Proceedings 56, JMLR.org 2016 [contents] - [i11]Dustin Tran, Minjae Kim, Finale Doshi-Velez:
Spectral M-estimation with Applications to Hidden Markov Models. CoRR abs/1603.08815 (2016) - [i10]Weiwei Pan, Finale Doshi-Velez:
A Characterization of the Non-Uniqueness of Nonnegative Matrix Factorizations. CoRR abs/1604.00653 (2016) - [i9]Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft:
Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks. CoRR abs/1605.07127 (2016) - [i8]Viktoriya Krakovna, Finale Doshi-Velez:
Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models. CoRR abs/1606.05320 (2016) - [i7]