1.6k citations · 2k across the 30 of their papers we have counts for
3 papers · 2 filters
Towards Accountable AI: Hybrid Human-Machine Analyses for Characterizing System Failure
Besmira Nushi, Ece Kamar, Eric Horvitz
As machine learning systems move from computer-science laboratories into the open world, their accountability becomes a high priority problem. Accountability requires deep understa…
Investigating Human + Machine Complementarity for Recidivism Predictions
Sarah Tan, Julius Adebayo, Kori Inkpen +1
When might human input help (or not) when assessing risk in fairness domains? Dressel and Farid (2018) asked Mechanical Turk workers to evaluate a subset of defendants in the ProPu…
Discovering Blind Spots in Reinforcement Learning
Ramya Ramakrishnan, Ece Kamar, Debadeepta Dey +2
Agents trained in simulation may make errors in the real world due to mismatches between training and execution environments. These mistakes can be dangerous and difficult to disco…