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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks


Nov 16, 2022
Jiayu Yao, Yaniv Yacoby, Beau Coker, Weiwei Pan, Finale Doshi-Velez

* Accepted at ICBINB Workshop, NeurIPS 2022 

   Access Paper or Ask Questions

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

Does the explanation satisfy your needs?: A unified view of properties of explanations


Nov 10, 2022
Zixi Chen, Varshini Subhash, Marton Havasi, Weiwei Pan, Finale Doshi-Velez

* Short version accepted at NeurIPS 2022 workshops on Progress and Challenges in Building Trustworthy Embodied AI and Trustworthy and Socially Responsible Machine Learning 

   Access Paper or Ask Questions

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

Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry


Aug 05, 2022
Mark Penrod, Harrison Termotto, Varshini Reddy, Jiayu Yao, Finale Doshi-Velez, Weiwei Pan

* International Conference on Machine Learning. PMLR 162 (2022) 

   Access Paper or Ask Questions

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

Policy Optimization with Sparse Global Contrastive Explanations


Jul 13, 2022
Jiayu Yao, Sonali Parbhoo, Weiwei Pan, Finale Doshi-Velez

* Accepted at IMLH Workshop, ICML 2022 

   Access Paper or Ask Questions

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

Wide Mean-Field Bayesian Neural Networks Ignore the Data


Feb 23, 2022
Beau Coker, Wessel P. Bruinsma, David R. Burt, Weiwei Pan, Finale Doshi-Velez


   Access Paper or Ask Questions

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

Promises and Pitfalls of Black-Box Concept Learning Models


Jun 24, 2021
Anita Mahinpei, Justin Clark, Isaac Lage, Finale Doshi-Velez, Weiwei Pan


   Access Paper or Ask Questions

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

Wide Mean-Field Variational Bayesian Neural Networks Ignore the Data


Jun 13, 2021
Beau Coker, Weiwei Pan, Finale Doshi-Velez


   Access Paper or Ask Questions

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

Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks


Jul 14, 2020
Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez

* Accepted at the International Conference on Machine Learning (ICML) Workshop on Uncertainty and Robustness in Deep Learning (UDL) 2020 

   Access Paper or Ask Questions

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

BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty


Jul 12, 2020
Théo Guénais, Dimitris Vamvourellis, Yaniv Yacoby, Finale Doshi-Velez, Weiwei Pan

* ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning 

   Access Paper or Ask Questions

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

Learned Uncertainty-Aware (LUNA) Bases for Bayesian Regression using Multi-Headed Auxiliary Networks


Jul 08, 2020
Sujay Thakur, Cooper Lorsung, Yaniv Yacoby, Finale Doshi-Velez, Weiwei Pan

* ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning 

   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
>>