Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Vidéo
Explaining Decisions from Vision Models and Correcting them via Human Feedback
Deep networks have enabled unprecedented breakthroughs in a variety of computer vision tasks. While these models enable superior performance, their increasing complexity and lack of decomposability into individually intuitive components makes them hard to interpret.…
Vidéo
Kristin Lauter’s TED Talk on Private AI at Congreso Futuro
Recent leaps in the fields of computing and artificial intelligence offer us until recently unimaginable solutions in sectors that determine our well-being, such as health, safety, or food. Kristin Lauter talks about Private AI during…
Publication
Active Imitation Learning With Noisy Guidance
Publication
How good is good enough for COVID19 apps?
Publication
Learning to rank via combining representations
Blog de recherche Microsoft
Fairness and interpretability in AI: Putting people first
At the 2005 Conference on Neural Information Processing Systems, researcher Hanna Wallach found herself in a unique position—sharing a hotel room with another woman. Actually, three other women to be exact. In the previous years…
Projet
AI at Scale
AI at Scale is an applied research initiative that works to evolve Microsoft products with the adoption of deep learning for both natural language text and image processing. Our work is actively being integrated into…