Filter by Keyword:

14 Results

Poster
Mon 9:00 Selectivity considered harmful: evaluating the causal impact of class selectivity in DNNs
Matthew Leavitt, Ari Morcos
Poster
Mon 9:00 Shapley explainability on the data manifold
Christopher Frye, Damien De Mijolla, Tom Begley, Laurence Cowton, Megan Stanley, Ilya Feige
Poster
Mon 17:00 Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting
Sayna Ebrahimi, Suzanne Petryk, Akash Gokul, William Gan, Joseph E Gonzalez, Marcus Rohrbach, trevor darrell
Poster
Tue 9:00 Getting a CLUE: A Method for Explaining Uncertainty Estimates
Javier Antorán, Umang Bhatt, Tameem Adel, Adrian Weller, José Miguel Hernández Lobato
Oral
Wed 4:05 Getting a CLUE: A Method for Explaining Uncertainty Estimates
Javier Antorán, Umang Bhatt, Tameem Adel, Adrian Weller, José Miguel Hernández Lobato
Poster
Wed 17:00 NBDT: Neural-Backed Decision Tree
Alvin Wan, Lisa Dunlap, Daniel Ho, Jihan Yin, Scott Lee, Suzanne Petryk, Sarah A Bargal, Joseph E Gonzalez
Poster
Thu 17:00 A Learning Theoretic Perspective on Local Explainability
Jeffrey Li, Vaishnavh Nagarajan, Gregory Plumb, Ameet Talwalkar
Poster
Thu 17:00 Evaluation of Similarity-based Explanations
Kazuaki Hanawa, Sho Yokoi, Satoshi Hara, Kentaro Inui
Workshop
Fri 6:00 AIMOCC -- AI: Modeling Oceans and Climate Change
Luis Martí, Nayat Sánchez-Pi
Workshop
Fri 6:45 Responsible AI (RAI)
Ahmad Beirami, Emily Black, Krishna Gummadi, Hoda Heidari, Baharan Mirzasoleiman, Meisam Razaviyayn, Joshua Williams
Fri 7:00 Secular Trends in ML Research with Morgan Stanley and Friends
Workshop
Fri 8:50 PROBLEM AND SOLUTION DOCUMENTATION TEMPLATE FOR MACHINE LEARNING COMPETITIONS TO ENHANCE EXPLAINABILITY, REPRODUCIBILITY, AND COLLABORATION BETWEEN STAKEHOLDERS
Olubayo Hamzat
Workshop
Fri 12:05 Weakly Supervised Multi-task Learning for Concept-based Explainability
Vladimir Balayan
Workshop
Fri 12:20 Weakly Supervised Multi-task Learning for Concept-based Explainability - Q&A