Near Optimal Policy Optimization via REPS
Neural Information Retrieval: In search of meaningful progress (CIIR Talk Series, University of Massachusetts Amherst)
The emergence of deep learning based methods for search poses several challenges and opportunities not just for modeling, but also for benchmarking and measuring progress in the field. Some of these challenges are new, while…
Fairness-related harms in AI systems: Examples, assessment, and mitigation
AI has transformed modern life via previously unthinkable feats, from machines that can master the ancient board game Go and self-driving cars to developments we experience more routinely, such as virtual agents and personalized product…
Fairness-related harms in AI systems: Examples, assessment, and mitigation webinar
AI has transformed modern life via previously unthinkable feats, from machines that can master the ancient board game Go and self-driving cars to developments we experience more routinely, such as virtual agents and personalized product…
High-resolution networks (HRNets) for Semantic Segmentation
This is an official implementation of semantic segmentation for our TPAMI paper “Deep High-Resolution Representation Learning for Visual Recognition”.