New Frontiers in Imitation Learning

3 days ago
The ongoing explosion of spatiotemporal tracking data has now made it possible to analyze and model fine-grained behaviors in a wide range of domains. For instance, tracking data is now being collected for every NBA basketball game with players, referees, and the ball tracked at 25 Hz, along with annotated game events such as passes, […]

Small Deep Neural Networks – Their Advantages, and Their Design

4 days ago
Deep neural networks (DNNs) have led to significant improvements to the accuracy of machine-learning applications. For many problems, such as object classification and object detection, DNNs have led to levels of accuracy that are acceptable for commercial applications. In other words, thanks to DNNs, an ever-growing range of ML-enabled applications are now ready to be […]

Microsoft Translator in the Classroom

4 days ago
In July 2017, a group of Chinese students visiting from the University of Washington stopped by the Microsoft AI and Research offices to learn about Microsoft Translator’s speech translation technology. In this video, Will Lewis – Principal Technical PM for Microsoft Translator – demonstrated how the Translator live feature and Presentation Translator add-in for PowerPoint […]

Trading-Off Cost of Deployment Versus Accuracy for Predictive Models

1 week ago
Predictive models are finding an increasing number of applications in many industries. As a result, a practical means for trading-off the cost of deploying a model versus its effectiveness is needed. Our work is motivated by risk prediction problems in healthcare. Cost-structures in domains such as healthcare are quite complex, posing a significant challenge to […]

Articulated Human Pose Tracking with Inertial Sensors

1 week ago
Thus far, capturing human body motion has only been possible with precisely-positioned sensors and cameras in well-calibrated studio environments. This constraint has fundamentally restricted the application of motion-capture technology to low-no mobility scenarios. To precisely track motion, the state-of-the-art is to either use well-calibrated inertial or magnetic-position sensors tightly strapped to the body or high-speed […]

Constrained Temporal Variation in Speech

1 week ago
The characteristic durations of speech sounds vary considerably across languages, dialects, and even speakers of the same dialect. Analyses of increasingly large speech corpora reveal, however, that temporal variation in speech is highly constrained. Within a language/dialect, different speakers produce duration patterns — such as the distinction in length between tense and lax vowels — […]

Fundamentals of User Studies

1 week ago
Overview of important methods and techniques applied in user studies from the perspective of academic research, and also from the perspective of product development. The talk is ended with two examples of projects done at Microsoft Research India that used some of the methods and techniques discussed. See more on this video at


2 weeks ago
An overview of some aspects of multilingualism for those that are new to the field. This talk introduces important issues and concepts to have in mind when working on your research projects. See more on this video at

Spoken Dialog Systems – Task Oriented Systems

2 weeks ago
Tutorial on what actual dialog systems are like and the problems we have with them, based on lectures Alan gave at Carnegie Mellon University. See more on this video at

Understanding the Rapidly Developing Field of Mobile Mental Health

2 weeks ago
In recent years, there has been an explosion of interest in and research on the use of mental health technologies that aim to treat and manage mental health problems. From smartphone apps to bots, from machine learning to natural language processing, technology is poised to transform mental health service delivery. However, what out there is […]

The Edge of Machine Learning: Resource efficient ML in 2 KB RAM for the Internet of Things

2 weeks ago
Resource-efficient ML in 2 KB RAM for the Internet of Things See more on this video at

Counterfactual Multi-Agent Policy Gradients

4 weeks ago
Many real-world problems, such as network packet routing and the coordination of autonomous vehicles, are naturally modelled as cooperative multi-agent systems. In this talk, I overview some of the key challenges in developing reinforcement learning methods that can efficiently learn decentralised policies for such systems. I also propose a new multi-agent actor-critic method called counterfactual […]