Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
프로젝트
Platform for Situated Intelligence
The Platform for Situated Intelligence project focuses on constructing an open, extensible platform to enable the fast development of multimodal, integrative-AI systems.
동영상
Question Generation
While there have been many advances in machine reading comprehension to develop models that can answer questions, Microsoft Research Montreal has been working to teach machines to ask informative questions.
동영상
Towards Artificial General Intelligence
Microsoft Research Montreal has developed a suite of tasks that teach artificial agents how to seek information actively, by asking questions. We’ve also designed a deep neural agent that learns to accomplish these tasks through…
동영상
News QA Demo
Volumes of written text is produced everyday. While search engines do a great job of indexing this information, finding the most relevant and up to date information is a challenging task. Our state-of-the-art machine reading…
동영상
Research Demo on Children’s Stories and CNN News
Most of us read thousands of documents throughout our lives. Along with observation and communication, reading is one of the primary ways we learn. Almost all of human knowledge has been written down in some…
동영상
Game of Thrones: Marcy Demo
A demonstration of a deep learning bot (“Marcy”) answering reading comprehension questions about a plot summary of “Game of Thrones” plot summary.
동영상
Machine Reading Comprehension Demo
In this video we demonstrate how our technology can be used to read excerpts from books such as Harry Potter and more complex documents such as legal NDAs and medical journals.
동영상
Harry Potter & the Philosopher’s Stone Demo
Maluuba’s deep learning models reading excerpts from Harry Potter and answering questions based on comprehension.
동영상
Learning Optimal Interventions Under Uncertainty
A fundamental goal in data analysis is learning which actions (i.e. interventions) are optimal for producing a desired outcome within specific individuals or over an entire population. While advances in reinforcement learning, Bayesian optimization, and…
