Microsoft Research

With the increasing integration of machine learning into real systems, it is crucial that trained models are optimized to reflect real-world tradeoffs.

This talk will describe our recent work on designing image classification systems that, after an initial multi-task training phase, can automatically adapt to new tasks encountered at test time.

Online Learning Rate Adaptation with Hypergradient Descent: We introduce a general method for improving the convergence rate of gradient-based optimizers that is easy to implement and works well in

MSR AI Distinguished Talk Series: Learning over sets, subgraphs, and streams: How to accurately incorporate graph context in network models Although deep learning methods have been successfully

Computer scientists think often of "Ender's Game" these days.

There are lots of tools and materials that make it easy to design and prototype electronic devices.

From online shopping to social media websites, many applications are built using imperative languages like Java, Python or Ruby while store its data in a persistent relational database.

Although machine learning has witnessed rapid progress in the last decade, many current learning algorithms are very inefficient in terms of the amount of data it uses, and the time used to train

Episode 114 |

From Rural America to Silicon Valley – Making AI Serve Us All In this timely book written from the perspective of a technologist whose life started in rural America and wound its way to Silicon

Episode 113 | April 1, 2020 Brad Smith is the President of Microsoft and leads a team of more than 1400 employees in 56 countries.

The Microsoft Rocketbox Avatar library consists of 115 characters and avatars fully rigged and with high definition that was developed over the course of 10 years.

Video Figure accompanying CHI 2020 paper, demonstrating a novel haptic device that allows a white cane user to interact with a large, complex virtual environment.

The recent curation of large-scale databases with 3D surface scans of shapes has motivated the development of tools that better detect global-patterns in morphological variation.

Many tech companies are trying to build machines that detect people’s emotions, using techniques from artificial intelligence. Some companies claim to have succeeded already. Dr.

Episode 112 | March 25, 2020 Rangan Majumder is the Partner Group Program Manager of Microsoft’s Search and AI, and he has a simple goal: to make the world smarter and more productive.

Episode 02 | March 20, 2020 Crowdsourcing platforms and the gig economy have been around for a while. But are they equally accessible to all communities? Dr.

We describe a concept smartphone Display Cover, a secondary screen designed to improve productivity and convenience.

Popular games for smartphones and tablets focus on touchscreen-based interaction.

Episode 111 | March 18, 2020 Dr. Behnaz Arzani is a senior researcher in the Mobility and Networking group at MSR, and she feels your pain.

Machines are a long way from robustly solving open-world perception-control tasks, such as first-person view (FPV) aerial navigation.

Over the last year, ten teams from around the world have been participating in the DARPA Subterranean challenges.

Are you Exploiting Your Assumptions?

Fireside Chat: Susan Dumais and Aaron Courville See more at microsoft.com/en-us/research/video/fireside-chat-with-aaron-courville

Episode 110 | March 11, 2020 If you want an inside look at how a research idea goes from project to prototype to product, you should hang out with Gavin Jancke for a while.

Track : Fairness, Transparency and Privacy in Digital systems Astha Kapoor, Aapti Institute ; Emre Kiciman, Microsoft Research ; Yair Zick, National University of Singapore Track Moderator : Amit

Panel Discussion: Cyber Security – National Policy and Preparedness G Narendra Nath, joint Secretary, NCSC Subrata Rakshit, CAIR DRDO Track Moderator : Madhavan Mukund, Chennai Mathematical

Privacy & Security in Healthcare Bill Thies (Microsoft Research) in conversation with Dr.

Talk: Security & Privacy around Foundational Identity for Sovereign Nations – Anadi Mishra, Architect MOSIP & Sasikumar Ganesan Security Architect, MOSIP/India Stack See more at

Track on Verification – Sanjiva Prasad, IIT Delhi ; S P Suresh, CMI ; Aseem Rastogi, Microsoft Research.