Microsoft Research

Over recent years, machine learning techniques have achieved success in many real-world applications.

Very often information about social entities is scattered across multiple databases.

Episode 92 | October 2, 2019 If someone asked you what snow leopards and Vincent Van Gogh have in common, you might think it was the beginning of a joke.

Control theorists know for long that quadratic invariants, that is ellipsoids, are a good solution to bound the behavior of linear controllers, which constitute the heart of most control-command

Dialog-enabled smart assistants, which communicate via natural language and occupy human homes, have seen widespread adoption in recent years.

As a professor of pure mathematics, my job involves teaching, research, and outreach.

Earlier this year we (Lewis, Pereira, and Teague) examined the source code for the SwissPost e-voting system, intended to be used for Swiss elections in May.

Although Canada is quickly becoming a world leader in the use of online voting, a vacuum of cybersecurity standards, regulation, and public awareness has left online voting vendors largely to set

A range of explanation engines assist data analysts by performing feature selection over increasingly high-volume and high-dimensional data, grouping and highlighting commonalities among data points.

How does the brain beget the mind? How do molecules, cells, and synapses effect reasoning, intelligence, language, science?

Brain-computer interfaces (BCIs) offer a non-verbal and covert way for humans to interact with a machine.

A Short Introduction to DIMACS, Fred Roberts, DIMACS Fred Roberts gives an overview of the DIMACS center founded in 1989, after a nationwide competition, as an NSF Science and Technology Center

The explosion of available idea repositories—scientific papers, patents, product descriptions—represents an unprecedented opportunity to accelerate innovation and lead to a wealth of discoveries.

Large-scale systems are often subject to non-ideal conditions such as failures, stragglers, load imbalance, etc.

This paper presents GraphRex, an efficient, robust, scalable, and easy-to-program framework for graph processing on datacenter infrastructure.

LSM-based KV stores are designed to offer good write performance by capturing client writes in memory and only later flushing them to storage.

Property-based random testing, exemplified by frameworks such as Haskell's QuickCheck, works by testing an executable predicate (a property) on a stream of randomly generated inputs.

For autonomous robots to operate in the open, dynamically changing world, they will need to be able to learn a robust set of skills from relatively little experience.

The explosion of available idea repositories — scientific papers, patents, product descriptions — represents an unprecedented opportunity to accelerate innovation and lead to a wealth of discoveries.

Consider the problem of sequentially estimating quantiles of any distribution over a complete, fully-ordered set, based on a stream of i.i.d. observations.

In this talk I will present a work in progress on structured linear block codes.

Episode 91 | September 25, 2019 Dr. Eyal Ofek is a senior researcher at Microsoft Research and his work deals mainly with, well, reality. Augmented and virtual reality, to be precise.

Web pages define their appearance using Cascading Style Sheets.

Peer review is the backbone of scholarly research.

The Bellevue School District serves nearly 22,000 students east of Seattle, WA.

Microsoft Research Montréal interns share their experiences and recommendations for future interns.

Unsupervised image-to-image translation aims to map an image drawn from one distribution to an analogous image in a different distribution, without seeing any example pairs of analogous images.

How is player experience best labelled and, in turn, captured by a computational model? Which machine learning methods seem to be more appropriate for the task?

Episode 90 | September 18, 2019 Dr.

Due to the high computational cost of rendering 3-D graphics for virtual reality, 3-D sound rendering is typically limited to a small fraction of the total compute power.