Microsoft Research Lab – Redmond
News & features
In the news | Forbes
Microsoft Brings Enhanced NLP Capabilities To ONNX Runtime
Microsoft has announced that it has integrated an optimized implementation of BERT (Bidirectional Encoder Representations from Transformers) with the open source ONNX Runtime. Developers can take advantage of this implementation for scalable inferencing of BERT at an affordable cost.
In the news | WinBuzzer
Microsoft Open Sources BERT for ONNX Runtime
In December, Microsoft open sourced its ONNX Runtime inference engine. Now, the company says it also open-sourced an optimized version of BERT, a natural language model from Google, for ONNX.
In the news | VentureBeat
Microsoft open-sources ONNX Runtime model to speed up Google’s BERT
Microsoft Research AI today said it plans to open-source an optimized version of Google’s popular BERT natural language model designed to work with the ONNX Runtime inference engine. Microsoft uses to the same model to lower latency for BERT when…
In the news | ZDNet
Microsoft makes performance, speed optimizations to ONNX machine-learning runtime available to developers
Microsoft is open sourcing and integrating some updates it it has made in deep-learning models used for natural-language processing. On January 21, the company announced it is making available to developers these optimizations by integrating them into the ONNX Runtime.
In the news | Rolls-Royce News
Technology breakthrough offers hope for people silenced by disability
Microsoft and other companies joined forces to help Rolls-Royce create new AI technology that will allow people with motor neurone disease (MND) to have a conversation in their own voice, even after they have lost the ability to speak.
Adaptive systems, machine learning and collaborative AI with Dr. Besmira Nushi
With all the buzz surrounding AI, it can be tempting to envision it as a stand-alone entity that optimizes for accuracy and displaces human capabilities. But Dr. Besmira Nushi, a senior researcher in the Adaptive Systems and Interaction group at…
Awards | VentureBeat
Microsoft Research’s Lin Xiao earns Test of Time award at NeurIPS
Lin Xiao’s paper Dual Averaging Method for Regularized Stochastic Learning and Online Optimization, won the Test of Time Award paper at NeurIPS 2019. His paper was selected for having made an important contribution, lasting impact, and broad appeal as papers have…
Project Petridish: Efficient forward neural architecture search
| Debadeepta Dey
Having experience in deep learning doesn’t hurt when it comes to the often mysterious, time- and cost-consuming process of hunting down an appropriate neural architecture. But truth be told, no one really knows what works the best on a new…
Game of Drones at NeurIPS 2019: Simulation-based drone-racing competition built on AirSim
| Ratnesh Madaan and Ashish Kapoor
Drone racing has transformed from a niche activity sparked by enthusiastic hobbyists to an internationally televised sport. In parallel, computer vision and machine learning are making rapid progress, along with advances in agile trajectory planning, control, and state estimation for…