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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis


Jun 17, 2022
Shayegan Omidshafiei, Andrei Kapishnikov, Yannick Assogba, Lucas Dixon, Been Kim


   Access Paper or Ask Questions

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

Human-Centered Concept Explanations for Neural Networks


Feb 25, 2022
Chih-Kuan Yeh, Been Kim, Pradeep Ravikumar

* book chapter of Neuro-Symbolic Artificial Intelligence: The State of the Art, volume: 342, p.337 - 352, 2022 

   Access Paper or Ask Questions

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

Subgoal-Based Explanations for Unreliable Intelligent Decision Support Systems


Jan 11, 2022
Devleena Das, Been Kim, Sonia Chernova


   Access Paper or Ask Questions

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

Acquisition of Chess Knowledge in AlphaZero


Nov 27, 2021
Thomas McGrath, Andrei Kapishnikov, Nenad Tomašev, Adam Pearce, Demis Hassabis, Been Kim, Ulrich Paquet, Vladimir Kramnik

* 69 pages, 44 figures 

   Access Paper or Ask Questions

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

Best of both worlds: local and global explanations with human-understandable concepts


Jun 16, 2021
Jessica Schrouff, Sebastien Baur, Shaobo Hou, Diana Mincu, Eric Loreaux, Ralph Blanes, James Wexler, Alan Karthikesalingam, Been Kim


   Access Paper or Ask Questions

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

DISSECT: Disentangled Simultaneous Explanations via Concept Traversals


May 31, 2021
Asma Ghandeharioun, Been Kim, Chun-Liang Li, Brendan Jou, Brian Eoff, Rosalind W. Picard


   Access Paper or Ask Questions

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

Debugging Tests for Model Explanations


Nov 10, 2020
Julius Adebayo, Michael Muelly, Ilaria Liccardi, Been Kim

* A shorter version of this work will appear at Neurips 2020 

   Access Paper or Ask Questions

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

Concept Bottleneck Models


Jul 09, 2020
Pang Wei Koh, Thao Nguyen, Yew Siang Tang, Stephen Mussmann, Emma Pierson, Been Kim, Percy Liang

* ICML 2020 

   Access Paper or Ask Questions

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

On Concept-Based Explanations in Deep Neural Networks


Oct 17, 2019
Chih-Kuan Yeh, Been Kim, Sercan O. Arik, Chun-Liang Li, Pradeep Ravikumar, Tomas Pfister


   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
4
>>