19.05.17 3:21 Holographic Near-Eye Displays for Virtual and Augmented Reality
We present novel designs for virtual and augmented reality near-eye displays based on phase-only holographic projection.
121 441
88.2
19.05.17 22:07 From GANs to Variational Divergence Minimization
An important problem in achieving general artificial intelligence is the data-efficient learning of representations suitable for causal reasoning, planning, and decision making.
2 473
14.1
18.05.17 18:11 Learning to Code: Machine Learning for Program Induction
The task of synthesizing programs given only example input-output behaviour is experiencing a surge of interest in the machine learning community.
10 732
22.7
17.05.17 1:03:09 Accountable Algorithms
Important decisions about people are increasingly made by algorithms: Votes are counted; voter rolls are purged; financial aid decisions are made; taxpayers are chosen for audits; air travelers are
805
44.3
17.05.17 1:26 Microsoft Security Risk Detection Helps Digital Transaction Management company DocuSign
Taking paper-driven processes online isn’t easy – but keeping it secure is a whole other matter.
1 671
61.6
16.05.17 6:12 Transform Data by Example, a Microsoft Garage project
Transform Data by Example is an example-driven search engine that can help you find functions for your data wrangling task. It is an Excel Add-In, powered by a backend service on Azure.
15 480
73.3
15.05.17 58:46 Nonlinear ICA using temporal structure: a principled framework for unsupervised deep learning
Unsupervised learning, in particular learning general nonlinear representations, is one of the deepest problems in machine learning.
2 836
14.7
15.05.17 58:26 Predicting 3D Volume and Depth from a Single View
A single glimpse is hardly enough to triangulate the 3D shapes of a scene. However, training examples are readily available, so statistical models can be trained to map appearance to shape.
12 044
25.6
15.05.17 56:00 Generalizing Convolutions for Deep Learning
Arguably, most excitement about deep learning revolves around the performance of convolutional neural networks and their ability to automatically extract useful features from signals.
22 124
14.8
15.05.17 57:42 Neural Question Answering over Knowledge Graphs
Questions in real-world scenarios are mostly factoid, such as "any universities in Seattle?''. In order to answer factoid questions, a system needs to extract world knowledge and reason over facts.
6 683
35
12.05.17 1:10:12 Automating and Testing Program Transformations using Program Synthesis
Automatic program transformation tools can be valuable for programmers to help them with refactoring tasks, and for Computer Science students in the form of tutoring systems that suggest repairs to
618
33.9
11.05.17 1:03:24 Seeing Experience from Many Angles: Educational Game Design as a Data-Informed Craft
Increasingly, educational games have become an established part of the instructional landscape, however designing a compelling and effective instructional game remains a challenge.
193
11.05.17 1:03:36 Streaming Lower Bounds for Approximating MAX-CUT
We consider the problem of estimating the value of MAX-CUT in a graph in the streaming model of computation.
635
34.9
11.05.17 1:01:57 Information-Performance Tradeoffs in Control
Consider a flying drone controlled from the ground by an observer who communicates with it via wireless.
412
27.1
11.05.17 1:25:32 Combining Algorithms and Humans for Large-Scale Data Integration
Modern enterprises collect data from their operations and the web, and strongly depend on the collected data to make important decisions.
288
10.05.17 1:30 Project Prague - The Conductor - Behind the Scenes
Microsoft Project Prague, part of Cognitive Services, is a cutting edge, easy-to-use SDK that helps developers and UX designers incorporate custom gestures into their apps.
546
12.7
10.05.17 0:51 Project Prague - The Conductor
Microsoft Project Prague, part of Cognitive Services, is a cutting edge, easy-to-use SDK that helps developers and UX designers incorporate custom gestures into their apps.
666
12
10.05.17 1:40 Project Prague - The Producer - Behind the Scenes
Microsoft Project Prague, part of Cognitive Services, is a cutting edge, easy-to-use SDK that helps developers and UX designers incorporate custom gestures into their apps.
6 839
142.1
10.05.17 1:02 Project Prague - The Producer
Microsoft Project Prague, part of Cognitive Services, is a cutting edge, easy-to-use SDK that helps developers and UX designers incorporate custom gestures into their apps.
10 860
240.9
10.05.17 1:54 Project Prague - Demos
Microsoft Project Prague, a part of Cognitive Services, is a cutting edge, easy-to-use SDK that helps developers and UX designers incorporate custom gestures into their apps.
14 968
57.7
09.05.17 4:47 Pelican Cold-storage System Demo
Pelican is a disk-based rack-scale cold data store. It has a converged rack-scale design in which resources, such as power and cooling are provisioned just for the requirements of the workload.
2 868
25.5
05.05.17 1:30:56 Data Science Education at the Heart of the 21st Century University
The Research University, rooted in the Land-Grant College Act at the outset of industrialization and transformed post-war with "Science the Endless Frontier" and GI Bill participation, is
737
13.3
04.05.17 5:04 Thumb + Pen Interaction on Tablets
Thumb + Pen Interaction on Tablets addresses the simultaneous, and complementary, use of pen & touch modalities for interaction in laptop scenarios, such as when using a Surface tablet on the couch
41 236
44.6
04.05.17 5:27 WritLarge: Ink Unleashed by Unified Scope, Action, & Zoom
WritLarge is a prototype system from Microsoft Research for the 84″ Microsoft Surface Hub, a large electronic whiteboard supporting both pen and multi-touch input.
4 595
21.8
04.05.17 2:00 Sparcs
Video about SPARCS See more on this video at microsoft.com/en-us/research/video/sparcs-video
487
32.1
04.05.17 2:34 Sparse Haptic Proxy: touch feedback in virtual environments
Microsoft Research researchers—Eyal Ofek, Christian Holz, Hrvoje Benko, and Andy Wilson, along with Lung-Pan Chen, a visiting intern from HPI, Germany—has proposed a solution that can help us feel
2 113
30.3
02.05.17 58:57 Quantum query complexity of entropy estimation
Estimation of Shannon and Renyi entropies of unknown discrete distributions is a fundamental problem in classical statistical property testing that has been intensively studied by the communities of
918
19.9
19.04.17 1:01:52 Unearthing Concurrency Bugs in Cloud-Scale Distributed Systems
Users demand for 24/7 dependability of cloud services. Unfulfilled dependability is costly, yet, there are complex challenges to reach an ideal dependability.
476
39.3
19.04.17 1:05:59 Modeling Context in Eventful Human-Machine Communications
Building AI systems that can process user input, understand it, and generate an engaging and contextually-relevant output in response, has been one of the longest-running goals in AI.
1 227
26.9
19.04.17 46:14 Neural Program Learning from Input-Output Examples
Most deep learning research focuses on learning a single task at a time - on a fixed problem, given an input, predict the corresponding output.
2 416
22.7