Microsoft Research

Storage systems make persistence guarantees even if the system crashes at any time, which they achieve using recovery procedures that run after a crash.

Deep learning has had enormous success on perceptual tasks but still struggles in providing a model for inference.

Fireside Chat with David Blei and Susan Dumais. See more in this series at microsoft.com/en-us/research/videos/ai-distinguished-lecture-series

Microsoft Research had the pleasure of hosting Bill Gates at this year’s Faculty Summit for a conversation on the Future Of Work with Eric Horvitz.

Streaming Analytics has become an indispensable tool for any agile organization.

The success of deep convolutional architectures is often attributed in part to their ability to learn multiscale and invariant representations of natural signals.

Recent developments in AI and Machine Learning (ML) are revolutionizing traditional technologies for health and education by enabling more intelligent therapeutic and learning tools that can

Elliptic curve groups have been a popular choice in the implementation of traditional and post-quantum cryptographic schemes, including Diffie-Hellman type key-exchange protocols and digital

Starting June 1st, we are holding a competition on sample-efficient reinforcement learning using human priors.

We introduce and formalize a new notion of password-based threshold token authentication, which protects password-based authentication against single point of failures.

Episode 83 | July 17, 2019 Dr.

High-resolution land cover mapping is a process of assigning land use labels, such as “impervious surface,” or “tree canopy” to each pixel in high resolution (&lt1m) aerial or satellite imagery.

The goal of Physics ∩ ML is to bring together researchers from machine learning and physics to learn from each other and push research forward together.

My group develops systems to help people manage information and share it with others.

Causal inference from observational data is a vital problem, but it comes with strong assumptions.

Learning from interaction with the environment -- trying untested actions, observing successes and failures, and tying effects back to causes -- is one of the first capabilities thought of when

Episode 82 | June 26, 2019 If you’re like me, you’re no longer amazed by how all your technologies can work for you. Rather, you’ve begun to take for granted that they simply should work for you.

This talk will focus on cross-device interaction, including techniques for integrating multiple devices in knowledge work, with a focus on interaction techniques as realized in working systems. Dr.

Value-function approximation methods that operate in batch mode have foundational importance to reinforcement learning (RL).

The learning with errors (LWE) problem introduced by Regev (STOC'05) is one of the fundamental problems in lattice-based cryptography.

Scientific computing is increasingly incorporating the advancements in machine learning and the ability to work with large amounts of data.

Episode 81 | June 19, 2019 Dr.

Vision-Language Navigation is the task of navigating an embodied agent to carry out natural language instructions inside real 3D environments.

Exercise your mind and eyes with match two! Flip cards to reveal images, and match up all the pairs to win the game. See more at aka.ms/eyesfirst

Practice your skills by using your eyes to slide the tiles back into order to solve the puzzles. See more at aka.ms/eyesfirst

Learn how to dwell with your eyes and navigate Lunita through each maze to help her find her way home. See more at aka.ms/eyesfirst

Use your eyes to slide all the tiles in one of four directions and collide like numbers to double them until you reach 2048 (or higher). See more at aka.ms/eyesfirst

Introduction to the Eyes First Collection of Games, including the system requirements, where to find the games for download and, and how to calibrate the software.

Episode 80 | June 12, 2019 You may not know who Dr. Andrew Fitzgibbon is, but if you’ve watched a TV show or movie in the last two decades, you’ve probably seen some of his work.

We present Vision-based Navigation with Language-based Assistance (VNLA), a grounded vision-language task where an agent with visual perception is guided via language to find objects in