Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Blog de recherche Microsoft
When bias begets bias: A source of negative feedback loops in AI systems
Is bias in AI self-reinforcing? Decision-making systems that impact criminal justice, financial institutions, human resources, and many other areas often have bias. This is especially true of algorithmic systems that learn from historical data, which…
Vidéo
Perspectives on Cross-Validation
Cross-validation is probably the most widely used method for risk estimation in machine learning and statistics. However, analyzing it and comparing it to the data splitting estimator has proved difficult. In the first part of…
Blog de recherche Microsoft
By making text-based games more accessible to RL agents, Jericho framework opens up exciting natural language challenges
You’re in a field. In front of you, there’s a white house. The door is boarded shut. The immediate challenge—investigate the house. The game—Zork I: The Great Underground Empire, a treasure-seeking adventure in which you’ll…
Vidéo
Exploring Reinforcement Learning Methods from Algorithm to Application
Reinforcement learning (RL) is a systematic approach to learning and decision making under uncertainty. Developed and studied for decades, recent combinations of RL with modern deep learning have led to impressive demonstrations of the capabilities…
Webinaire
Exploring reinforcement learning methods from algorithm to application webinar
In this webinar led by Microsoft researcher Dr. Katja Hofmann, a Principal Researcher in the Game Intelligence group at Microsoft Research Cambridge, learn about the foundations of RL—elegant ideas giving rise to agents that can learn extremely…
Blog de recherche Microsoft
Are all samples created equal?: Boosting generative models via importance weighting
There is a growing interest in the use of deep generative models for sampling high-dimensional data; examples include high-resolution natural images, long-form text generation, designing pharmaceutical drugs, and creating new materials at the molecular level.…
Projet
Skeletal Tracking on Azure Kinect
Microsoft has released a new RGB-D sensor called Azure Kinect. I'm involved in developing the skeletral tracking for Azure Kinect. It consists of 2D pose estimation and 3D model fitting. The 2D pose estimation is…
Événement
Inclusive Data Visualization Workshop
This workshop will bring together data visualization researchers, accessibility researchers, as well as representatives from disability organizations to identify the current problems, to discuss possible solutions, and to create a roadmap for research on the…