Microsoft Research

Emerging energy-harvesting devices (EHDs) are computer systems that operate using energy extracted from their environment, even from low-power sources like ambient radio-frequency energy.

The promise and scale of mobile money has ignited huge interest in digital finance products in emerging markets, and is genuinely transforming these countries by providing access to formal financial

A brief talk on why diversity in games is more than a buzzword and should be a consideration from day one of development.

The alliance between AI and economics is making an ever-growing societal impact.

A common technique for solving integer programming problems is to first relax the problem to a linear program, in which the assignments may be fractional.

In a classical problem in scheduling, one has n unit size jobs with a precedence order and the goal is to find a schedule of those jobs on m identical machines as to minimize the makespan.

Relating tensor product representations to lamda-calculus, tree-adjoining grammars, other 'vector symbolic architectures', and the brain - Part 7 Topics that will be discussed in this final lecture

This talk will present the design and soundness proof of Verasco, a formally verified static analyzer for most of the ISO C99 language (excluding recursion and dynamic allocation), developed using

Architects and the semiconductor industry as a whole is faced with a unique challenge of improving performance and reducing power consumption of future microprocessors with almost no gain coming

Social conventions are the foundation of social cooperation and productive economic activity, yet very little is known about how and when they form.

The gauge color code is a quantum error-correcting code with local syndrome measurements that, remarkably, admits a universal transversal gate set without the need for resource-intensive magic state

Spectral inference provides fast algorithms and provable optimality for latent topic analysis.

How Much Information Does a Human Translator Add to the Original and Multi-Source Neural Translation?

Millions of network cameras have been deployed.

Nature in the City examines the past, present, and future of nature in Bangalore, one of India's largest cities. Though threatened, nature in the city exhibits a remarkable tenacity.

Over the past few years, virtual reality has experienced a remarkable resurgence.

Supervised learning algorithms can be understood not only as a set of techniques for building accurate models of data, but also as design tools that can enable rapid prototyping, iterative

In the past several years, there has been a lot of progress on combinatorial optimization.

Characterizing the computational complexity of statistical inference problems is an outstanding open problem.

Coloring the Universe: Many images of the Universe are spectacular, but are they "real"?

Encoding discrete symbol structures as numerical vectors for neural network computation enables the similarity structure inherent in vectorial representations to yield generalizations that reflect

Two talks from the 37th UW/MS Symposium in Computational Linguistics are featured: Using IGT with INTENT: Automatically Enriching Interlinear Glossed Text (IGT) and Discovering Outcomes via

Word embeddings are often constructed with discriminative models such as deep nets and word2vec.

Logarithmic Time Online Multiclass prediction: We study the problem of multiclass classification with an extremely large number of classes (k), with the goal of obtaining train and test time

I envision a system that enables successful collaborations between humans and machine learning models by harnessing the relative strength to accomplish what neither can do alone.

What symptoms are associated with the patient's genotype? Did patients treated with medication fare better than patients treated surgically?

This talk will survey a variety of classical results on the representation power of neural networks, and then close with a new result separating shallow and deep networks: namely, there exist

Security is a global concern, requiring efficient, randomized allocation and scheduling of limited security resources.

e-NABLE is an online community that designs, customizes, fabricates, and disseminates 3D-printed prosthetic hands and arms for free.

Microsoft Research New England focuses on interdisciplinary work, integrating the more mathematical and algorithmic sciences with both the social sciences and aspects of the biomedical sciences.