Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Towards the Use of Saliency Maps for Explaining Low-Quality Electrocardiograms to End Users


Jul 06, 2022
Ana Lucic, Sheeraz Ahmad, Amanda Furtado Brinhosa, Vera Liao, Himani Agrawal, Umang Bhatt, Krishnaram Kenthapadi, Alice Xiang, Maarten de Rijke, Nicholas Drabowski

* Accepted to ICML 2022 Workshop on Interpretable ML in Healthcare 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Eliciting and Learning with Soft Labels from Every Annotator


Jul 02, 2022
Katherine M. Collins, Umang Bhatt, Adrian Weller


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Perspectives on Incorporating Expert Feedback into Model Updates


May 13, 2022
Valerie Chen, Umang Bhatt, Hoda Heidari, Adrian Weller, Ameet Talwalkar


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

On the Utility of Prediction Sets in Human-AI Teams


May 03, 2022
Varun Babbar, Umang Bhatt, Adrian Weller

* Accepted at IJCAI 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Approximating Full Conformal Prediction at Scale via Influence Functions


Feb 02, 2022
Javier Abad, Umang Bhatt, Adrian Weller, Giovanni Cherubin

* 18 pages, 15 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates


Dec 09, 2021
Dan Ley, Umang Bhatt, Adrian Weller

* Accepted as a conference paper to AAAI 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement


Jul 13, 2021
Umang Bhatt, Isabel Chien, Muhammad Bilal Zafar, Adrian Weller

* 30 pages, 32 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Do Concept Bottleneck Models Learn as Intended?


May 10, 2021
Andrei Margeloiu, Matthew Ashman, Umang Bhatt, Yanzhi Chen, Mateja Jamnik, Adrian Weller

* Accepted at ICLR 2021 Workshop on Responsible AI 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

δ-CLUE: Diverse Sets of Explanations for Uncertainty Estimates


May 08, 2021
Dan Ley, Umang Bhatt, Adrian Weller

* Appeared as a workshop paper at ICLR 2021 (Responsible AI | Secure ML | Robust ML) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
>>