Microsoft Research

How can we explain the predictions of a black-box model?

This lecture is about implementing Byzantine fault tolerant state machine replication.

An overview of social networks and social network analysis. See more on this video at microsoft.com/en-us/research/video/social-network-analysis

We introduce a neural network with a recurrent attention model over a possibly large external memory.

VRoamer: Generating On The Fly VR Experiences While Walking Inside Large, Unknown Real-World Building Environments VRoamer is a novel proof of concept system that enables a user to play a virtual

Jan Nelson, Senior Program Manager at Windows Live International, teaches you how to create multilingual apps easily to reach more markets.

Microsoft Research has an on-going pilot in Bellevue, Washington for active traffic monitoring of traffic intersections live 24X7.

In the popular field of text to speech, the goal is to transform the written or printed word into speech that is natural and intelligible.

The "active learning" model is motivated by scenarios in which it is easy to amass vast quantities of unlabeled data (images and videos off the web, speech signals from microphone recordings, and so

TextWorld is a text-based game generator and sandbox learning environment for reinforcement learning agents. Watch this video to get started with using TextWorld!

Occasionally the office of the CTO, David Vaskevitch, sits down with some of Microsoft's most influential technical employees to capture their stories.

For several decades people have tried to write computer programs that can find proofs of mathematical statements.

A quick introduction to WikiBhasha beta. For more information on developing translation apps using Microsoft Translator, visit microsoft.com/translator/products.aspx

Writing papers and giving talks are key skills for any researcher, but they arenΓÇÖt easy.

The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the

Augmented Reality requires accurate camera pose estimates to correctly render virtual graphics into the real world.

We study the performance and user experience of two popular mainstream text entry devices, desktop keyboards, and touchscreen keyboards, for use in Virtual Reality (VR) applications.

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

I will present NeuroSAT, a message passing neural network that learns to solve SAT problems after only being trained as a classifier to predict satisfiability.

Microsoft Research is committed to investing in the future of computer science research through its Internship program as illustrated through the story of Pushmeet Kohli.

With cloud computing, users can access their personal data anywhere and anytime.

Deep neural networks (DNNs) have led to significant improvements to the accuracy of machine-learning applications.

Single-channel speech enhancement using deep neural networks (DNNs) has shown promising progress in recent years.

How should someone exploit photonics in computing?

The complexity of cells and their ability to process information has a lot in common with computers.

Microsoft Translator is the first end-to-end speech translation solution optimized for real-life conversations (vs. simple human to machine commands) available on the market.

Microsoft Research – 18 августа 2016, 19:02

Microsoft Project AirSim provides a rich set of tools that enables you to rapidly create custom machine learning capabilities.

Source code search can be seen as part of a larger process in which a programmer uses a range of development tools to help answer questions about a code base.