Research
Developing efficient algorithms that power faster, smarter, and more reliable computing across diverse applications.
The vision and learning group at CVT (Center for Vision Technologies) at SRI has developed a framework and a suite of algorithms for machine learning in data scarce conditions. We present our results on zero…
Human intelligence involves comprehending new situations through a rich model of the world. Given a single image from a movie, or a paragraph from a novel, we can easily infer people’s intentions, mental states, and…
Microsoft is excited to be part of the PPoPP/HPCA/CGO 2019 co-located conferences and is a Gold sponsor of PPoPP 2019 and HPCA 2019. Stop by our booth to learn about our latest research and find…
One challenge with AI algorithmic fairness is that one usually has to know the potential group(s) that an algorithm might discriminate against in the first place. However, in joint work with Maria De-Arteaga, Nathaniel Swinger,…
Episode 63, February 13, 2019 – Dr. Varma tells us all about extreme classification (including where in the world you might actually run into 10 or 100 million options), reveals how his Parabel and Slice…
Varma’s team published a paper that exploded the number of choices that could be considered from a search engine from five thousand to ten million. This changed the nature of the game and led to…
Northwest Database Society Annual Meeting Session 3: Open-Source Technologies for Streaming and State Management, Improving Optimistic Concurrency Control Through Transaction Batching and Operation Reordering, Towards a Learning Optimizer for Shared Clouds, and more. Agenda: 1:15…
