Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Video
MSR Cambridge Lecture Series: An Introduction to Graph Neural Networks: Models and Applications
MSR Cambridge, AI Residency Advanced Lecture Series An Introduction to Graph Neural Networks: Models and Applications Got it now: “Graph Neural Networks (GNN) are a general class of networks that work over graphs. By representing…
Podcast
Autonomous systems, aerial robotics and Game of Drones with Gurdeep Pall and Dr. Ashish Kapoor
There’s a lot of excitement around self-driving cars, delivery drones, and other intelligent, autonomous systems, but before they can be deployed at scale, they need to be both reliable and safe. That’s why Gurdeep Pall,…
Microsoft Research Blog
Optimistic Actor Critic avoids the pitfalls of greedy exploration in reinforcement learning
One of the core directions of Project Malmo is to develop AI capable of rich interactions. Whether that means learning new skills to apply to challenging problems, understanding complex environments, or knowing when to enlist…
Publication
OASIS: ILP-Guided Synthesis of Loop Invariants
Microsoft Research Blog
Icebreaker: New model with novel element-wise information acquisition method reduces cost and data needed to train machine learning models
In many real-life scenarios, obtaining information is costly, and getting fully observed data is almost impossible. For example, in the recruiting world, obtaining relevant information (in other words, a feature value) for a company could…
Event
PhD Workshop on Next-Generation Cloud Infrastructure
Microsoft Research Cambridge is organizing a workshop where PhD students working on topics relevant to the next-generation cloud infrastructure in Europe are invited to participate. During this two-day workshop, the students will have the opportunity…
Microsoft Research Blog
Logarithmic mapping allows for low discount factors by creating action gaps similar in size
While reinforcement learning (RL) has seen significant successes over the past few years, modern deep RL methods are often criticized for how sensitive they are with respect to their hyper-parameters. One such hyper-parameter is the…
Podcast
Program synthesis and the art of programming by intent with Dr. Sumit Gulwani
Dr. Sumit Gulwani is a programmer’s programmer. Literally. A Partner Research Manager in the Program Synthesis, or PROSE, group at Microsoft Research, Dr. Gulwani is a leading researcher in program synthesis and the inventor of…
