Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Project
Healthcare: Digital Doctor
Goal: Digital Doctor is a doctor assistant bot, which can help doctor to improve self ability and also answer patients questions automatically Demo: Auto QnA: http://msraml.cloudapp.net/home/manage.html Medical KB: http://msraml-s004:2521/ Techniques： KB Construction 知识字典建立 问题：…
Project
Kable
Goal: Kable is to extract structured knowledge from semi-structured Web site. Around 25% Web pages are of semi-structured, which contains lots of knowledge and are template generated web pages. Kable can learn the template across…
Project
Conceptualization
The Conceptualization model aims to map text format entities into semantic concept categories with some probabilities, which may depend on the context texts of the entities. As an example, “Microsoft” could be automatically mapped to…
Microsoft Research Blog
Boosting fitness and workplace performance looks to machine learning for answers
By Miran Lee, Principal Research Program Manager, Microsoft Research A field study exploring the usability of integrating fitness equipment into a workstation environment has researchers looking to tap next-generation machine learning innovations to address the…
Video
Improving Reinforcement Learning with Human Input
Although reinforcement learning (RL) has had many successes, significant amounts of time and/or data can be required to reach acceptable performance. If agents or robots are to be deployed in real world environments, it is…
Publication
No-Regret Replanning Under Uncertainty
Video
Intern talk: Understanding and Mitigating Solver Instability in Verification Tools
Abstract: Program verification tools such as Dafny and F* rely on Z3, an SMT-based automated theorem prover, to dispatch verification conditions. Z3’s powerful automation relieves programmers of the burden of writing tedious manual proofs. However,…
Project
Emotion Recognition for MS Cognitive Services
Emotion Recognition takes an image with faces as an input, and returns the confidence across a set of emotions for each face in the image, as well as bounding box for the face (using MS Face API). The…