Microsoft Research

Building predictive models first requires shaping the data into the right format to meet the mathematical assumptions of machine learning algorithms.

Deeply Learned Face Representation, presented by Xiaogang Wang from NIPS 2015.

Leon Gatys discusses deep learning at NIPS 2015.

Towards Glimpses of a New Science of Brains, Minds and Machines: Weaving Together Physics, Computer Science, and Neurobiology.

Probabilistic modelling provides a mathematical framework for understanding what learning is, and has therefore emerged as one of the principal approaches for designing computer algorithms that

In the talk, I will introduce a model of learning with Intelligent Teacher.

This tutorial will survey the state of the art in high-performance hardware for machine learning with an emphasis on hardware for training and deployment of deep neural networks (DNNs).

To help analysts better understand temporal queries, we developed StreamTrace, an interactive visualization tool that breaks down how a temporal query processes a given dataset, step-by-step.

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

Consider a branching tree with one root at the origin. Assuming that at the n -th level there are at least two vertices. Pick two of them by simple random sampling without replacement.

In addition to identifying the content within a single image, relating images and generating related images are critical tasks for image understanding.

Decades ago, when the audio industry was in its infancy, there was no way to get formal education in Audio Engineering.

Moderated by Eric Horvitz, Managing Director, Microsoft Research Panelists: Fei-Fei Li, Associate Professor, Stanford University Michael Littman, Professor of Computer Science, Brown University Josh

In this video, we focus our predictive approaches on real-world objects under fast motion and on-body projection, improving projection accuracy on fast moving targets.

Chair Gregg Gordon, President, Social Science Research Network, will lead a panel discussion on evaluation and impact "beyond citations" for articles, researchers, institutions.

In July 2014, a group of Microsoft employees got together to control an electric wheelchair via eye gaze.

Writing papers and giving talks are key skills for any researcher, but they aren't easy.

A Join circuit implemented in DNA.

The Bing Code Search add-in allows you to search and reuse code snippets directly inside Visual Studio.

Reinforcement learning is a body of theory and techniques for optimal sequential decision making developed in the last thirty years primarily within the machine learning and operations research

Deep Learning allows computational models composed of multiple processing layers to learn representations of data with multiple levels of abstraction.

Monte Carlo methods use random sampling to understand a system, estimate averages, or compute integrals.

Over the past few years, we have built large-scale computer systems for training neural networks, and then applied these systems to a wide variety of problems that have traditionally been very

Languages, compilers, and computer-aided design tools will be essential for scalable quantum computing, which promises an exponential leap in our ability to execute complex tasks.

In this video, we present Irides, a stereo HMD system that simultaneously attains quality, responsiveness and mobility.

RoomAlive is a proof-of-concept prototype that transforms any room into an immersive, augmented entertainment experience.

Digits, a wrist-worn gloveless sensor developed by Microsoft Research in Cambridge, U.K., enables 3-D computer interaction in any environment and is practical beyond computer gaming.

Speaker: Frank Seide This talk will introduce CNTK, Microsoft’s cutting-edge open-source deep-learning toolkit for Windows and Linux.

Speaker: Evelyne Viegas Given the investment and evidence of progress in Artificial Intelligence (AI) in the last five years, some suggest that it is merely a matter of time until AI matches

Chair: Will Lewis, Microsoft Research Projects and speakers: Learning Reusable Skills and Behavioral Hierarchies, Bruno Castro da Silva, Institute of Informatics of the Federal University of Rio