עקוב אחר
Amit Dhurandhar
Amit Dhurandhar
Principal Research Scientist, IBM
כתובת אימייל מאומתת בדומיין us.ibm.com - דף הבית
כותרת
צוטט על ידי
צוטט על ידי
שנה
Explanations based on the missing: Towards contrastive explanations with pertinent negatives
A Dhurandhar, PY Chen, R Luss, CC Tu, P Ting, K Shanmugam, P Das
Advances in Neural Information Proc. Systems, 2018
6362018
One explanation does not fit all: A toolkit and taxonomy of ai explainability techniques
V Arya, RKE Bellamy, PY Chen, A Dhurandhar, M Hind, SC Hoffman, ...
arXiv preprint arXiv:1909.03012, 2019
4042019
Predicting human olfactory perception from chemical features of odor molecules
A Keller, RC Gerkin, Y Guan, A Dhurandhar, G Turu, B Szalai, ...
Science 355 (6327), 820-826, 2017
2722017
Invariant risk minimization games
K Ahuja, K Shanmugam, K Varshney, A Dhurandhar
International Conference on Machine Learning, 145-155, 2020
2362020
Efficient data representation by selecting prototypes with importance weights
KS Gurumoorthy, A Dhurandhar, G Cecchi, C Aggarwal
2019 IEEE International Conference on Data Mining (ICDM), 260-269, 2019
157*2019
TED: Teaching AI to explain its decisions
M Hind, D Wei, M Campbell, NCF Codella, A Dhurandhar, A Mojsilović, ...
Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, 123-129, 2019
1362019
System and method for identifying procurement fraud/risk
A Dhurandhar, MR Ettl, BC Graves, RK Ravi
US Patent App. 14/186,071, 2015
852015
Ai explainability 360: An extensible toolkit for understanding data and machine learning models
V Arya, RKE Bellamy, PY Chen, A Dhurandhar, M Hind, SC Hoffman, ...
Journal of Machine Learning Research 21 (130), 1-6, 2020
81*2020
Model agnostic contrastive explanations for structured data
A Dhurandhar, T Pedapati, A Balakrishnan, PY Chen, K Shanmugam, ...
arXiv preprint arXiv:1906.00117, 2019
802019
Leveraging latent features for local explanations
R Luss, PY Chen, A Dhurandhar, P Sattigeri, Y Zhang, K Shanmugam, ...
Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data …, 2021
76*2021
Empirical or invariant risk minimization? a sample complexity perspective
K Ahuja, J Wang, A Dhurandhar, K Shanmugam, KR Varshney
Intl Conference on Learning Representations, 2021
692021
Deciding Fast and Slow: The Role of Cognitive Biases in AI-assisted Decision-making
C Rastogi, Y Zhang, D Wei, KR Varshney, A Dhurandhar, R Tomsett
ACM Conference On Computer- Supported Cooperative Work And Social Computing, 2022
672022
One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques.(2019)
V Arya, RKE Bellamy, PY Chen, A Dhurandhar, M Hind, SC Hoffman, ...
arXiv preprint arXiv:1909.03012, 1909
621909
Improving simple models with confidence profiles
A Dhurandhar, K Shanmugam, R Luss, P Olsen
Advances in Neural Information Proc. Systems, 2018
572018
Predicting natural language descriptions of mono-molecular odorants
ED Gutiérrez, A Dhurandhar, A Keller, P Meyer, GA Cecchi
Nature communications 9 (1), 4979, 2018
512018
Model agnostic multilevel explanations
KN Ramamurthy, B Vinzamuri, Y Zhang, A Dhurandhar
Advances in Neural Information Proc. Systems, 2020
48*2020
Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI
QV Liao, Y Zhang, R Luss, F Doshi-Velez, A Dhurandhar
Tenth AAAI Conference on Human Computation and Crowdsourcing, 2022
442022
Probabilistic characterization of nearest neighbor classifier
A Dhurandhar, A Dobra
International journal of machine learning and cybernetics 4, 259-272, 2013
422013
Tip: Typifying the interpretability of procedures
A Dhurandhar, V Iyengar, R Luss, K Shanmugam
arXiv preprint arXiv:1706.02952, 2017
402017
Ranking and tracking suspicious procurement entities
A Dhurandhar, M Ettl, BC Graves, G Maniachari, AT Mazzatti, RK Ravi
US Patent 10,467,631, 2019
352019
המערכת אינה יכולה לבצע את הפעולה כעת. נסה שוב מאוחר יותר.
מאמרים 1–20