11 citations · 25 across the 8 of their papers we have counts for
3 papers · 1 filter
MultiplexNet: Towards Fully Satisfied Logical Constraints in Neural Networks
Nicholas Hoernle, Rafael Michael Karampatsis, Vaishak Belle +1
We propose a novel way to incorporate expert knowledge into the training of deep neural networks. Many approaches encode domain constraints directly into the network architecture,…
Personalization in Human-AI Teams: Improving the Compatibility-Accuracy Tradeoff
Jonathan Martinez, Kobi Gal, Ece Kamar +1
AI systems that model and interact with users can update their models over time to reflect new information and changes in the environment. Although these updates may improve the ov…
The Phantom Steering Effect in Q&A Websites
Nicholas Hoernle, Gregory Kehne, Ariel D. Procaccia +1
Badges are commonly used in online platforms as incentives for promoting contributions. It is widely accepted that badges "steer" people's behavior toward increasing their rate of…