Andrew Ross
Andrew Ross
PhD student, Harvard University
Verified email at g.harvard.edu - Homepage
Title
Cited by
Cited by
Year
Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
AS Ross, F Doshi-Velez
Thirty-Second AAAI Conference on Artificial Intelligence, 1660-1669, 2017
3692017
Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations
AS Ross, MC Hughes, Doshi-Velez, Finale
Proceedings of the Twenty-Sixth International Joint Conference on Artificial …, 2017
3092017
Tackling Climate Change with Machine Learning
D Rolnick, PL Donti, LH Kaack, K Kochanski, A Lacoste, K Sankaran, ...
arXiv preprint arXiv:1906.05433 [cs, stat], 2019
296*2019
Human-in-the-loop interpretability prior
I Lage, AS Ross, B Kim, SJ Gershman, F Doshi-Velez
Advances in neural information processing systems 31, 2018
822018
Improving sepsis treatment strategies by combining deep and kernel-based reinforcement learning
X Peng, Y Ding, D Wihl, O Gottesman, M Komorowski, LH Lehman, ...
AMIA Annual Symposium Proceedings 2018, 887, 2018
422018
Design Continuums and the Path Toward Self-Designing Key-Value Stores that Know and Learn.
S Idreos, N Dayan, W Qin, M Akmanalp, S Hilgard, A Ross, J Lennon, ...
CIDR, 2019
412019
Hydrodynamic irreversibility in particle suspensions with nonuniform strain
JS Guasto, AS Ross, JP Gollub
Physical Review E 81 (6), 061401, 2010
232010
The neural lasso: Local linear sparsity for interpretable explanations
A Ross, I Lage, F Doshi-Velez
Workshop on Transparent and Interpretable Machine Learning in Safety …, 2017
122017
Learning qualitatively diverse and interpretable rules for classification
AS Ross, W Pan, F Doshi-Velez
arXiv preprint arXiv:1806.08716, 2018
92018
Ensembles of locally independent prediction models
A Ross, W Pan, L Celi, F Doshi-Velez
Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 5527-5536, 2020
82020
Improving counterfactual reasoning with kernelised dynamic mixing models
S Parbhoo, O Gottesman, AS Ross, M Komorowski, A Faisal, I Bon, ...
PloS one 13 (11), e0205839, 2018
72018
Assessment of a prediction model for antidepressant treatment stability using supervised topic models
MC Hughes, MF Pradier, AS Ross, TH McCoy, RH Perlis, F Doshi-Velez
JAMA network open 3 (5), e205308-e205308, 2020
62020
Learning key-value store design
S Idreos, N Dayan, W Qin, M Akmanalp, S Hilgard, A Ross, J Lennon, ...
arXiv preprint arXiv:1907.05443, 2019
52019
Evaluating the Interpretability of Generative Models by Interactive Reconstruction
A Ross, N Chen, EZ Hang, EL Glassman, F Doshi-Velez
Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems …, 2021
32021
Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement
AS Ross, F Doshi-Velez
arXiv preprint arXiv:2102.05185, 2021
32021
Refactoring Machine Learning
AS Ross, JZ Forde
NeurIPS 2018 Workshop on Critiquing and Correcting Trends in Machine Learning, 2018
22018
Learning Predictive and Interpretable Timeseries Summaries from ICU Data
N Johnson, S Parbhoo, AS Ross, F Doshi-Velez
arXiv preprint arXiv:2109.11043, 2021
2021
Right for the Right Reasons: Training Neural Networks to Be Interpretable, Robust, and Consistent with Expert Knowledge
AS Ross
Harvard University, 2021
2021
Generating interpretable predictions about antidepressant treatment stability using supervised topic models
MC Hughes, MF Pradier, AS Ross, TH McCoy, RH Perlis, F Doshi-Velez
medRxiv, 2020
2020
Controlled Direct Effect Priors for Bayesian Neural Networks
J Du, AS Ross, Y Shavit, F Doshi-Velez
NeurIPS 2019 Workshop on Bayesian Deep Learning, 2019
2019
The system can't perform the operation now. Try again later.
Articles 1–20