Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Publication
Truthful Aggregation of Budget Proposals
Publication
Fast Context Adaptation via Meta-Learning
Blog de recherche Microsoft
What’s in a name? Using Bias to Fight Bias in Occupational Classification
Bias in AI is a big problem. In particular, AI can compound the effects of existing societal biases: in a recruiting tool, if more men than women are software engineers, AI is likely to use…
Vidéo
On The Hardness of Reinforcement Learning With Value-Function Approximation (and The Lack of Understanding Thereof)
Value-function approximation methods that operate in batch mode have foundational importance to reinforcement learning (RL). Finite sample guarantees for these methods—which provide the theoretical backbones for empirical (“deep”) RL today—crucially rely on strong representation assumptions,…
Baladodiffusion
Machine teaching with Dr. Patrice Simard
Episode 78, May 29, 2019- Machine learning is a powerful tool that enables computers to learn by observing the world, recognizing patterns and self-training via experience. Much like humans. But while machines perform well when…
