Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Video
Research talk: Challenges in multi-tenant graph representation learning for recommendation problems
Recent research has shown that representations learned from user-user and user-item graphs can be used to improve recommendation performance. In this research, the recommendation model is often trained with representation learning. In project DEEGO, we…
Video
Panel discussion: Content moderation beyond the ban: Reducing borderline, toxic, misleading, and low-quality content
Public debate about content moderation focuses almost exclusively on removal, such as what is deleted and who is suspended. But what about content that is identified as “borderline,” which almost—but not quite—violates the guidelines? Faced…
Video
Research talk: Bucket of me: Using few-shot learning to realize teachable AI systems
We’re entering a technological era that is all about “me”—from personalized shopping recommendations to avatars, and even bespoke healthcare treatments. Deeper inspection of artificial intelligence (AI) systems, however, reveals that “me” is not really me.…
Video
Research talk: Multidimensional analysis of cloud-native software based on large-scale operation data
Dynamic and static analysis of source code has been widely used in software development practices for purposes such as reverse engineering, design issue detection, and fault localization. Cloud-native software, which is featured by containerized and…
Video
Research talk: SPTAG++: Fast hundreds of billions-scale vector search with millisecond response time
Current state-of-the-art vector approximate nearest neighbor search (ANNS) libraries mainly focus on how to do fast high-recall search in memory. However, extremely large-scale vector search scenarios present certain challenges. For example, hundreds of billions of…
Video
Fireside chat: Opportunities and challenges in human-oriented AI
A key challenge in developing novel AI technology is to ensure that resulting approaches and their applications fit well within the human environments they will be applied in. Recent research at Microsoft develops new approaches…
Video
Research talk: Privacy in machine learning research at Microsoft
Speaker: Melissa Chase, Principal Researcher, Microsoft Research Redmond Training modern machine learning models requires large amounts of data, and often that data may be private or confidential. The area of privacy-preserving machine learning looks at…
Video
Panel: Generalization in reinforcement learning
The ability for a reinforcement learning (RL) policy to generalize is a key requirement for the broad application of RL algorithms. This generalization ability is also essential to the future of RL—both in theory and…
Video
Demo: RAI Toolbox: An open-source framework for building responsible AI
Assessing and investigating machine learning (ML) models prior to deployment remains at the core of developing trustworthy and responsible artificial intelligence (AI). While different open-source tools have been proposed for assessing fairness, explainability, or errors…
Video
Research talk: Project Dexter: Machine learning and automatic decision-making for robotic manipulation
Robot technology has long held the promise of disrupting many important industries that involve dexterous object manipulation in weakly structured environments, including healthcare, agriculture, and infrastructure maintenance. The increasing versatility of robotic manipulation hardware seemingly…
