Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Vidéo
Research talk: Causal learning: Discovering causal relations for out-of-distribution generalization
Machine learning models should be explainable and robust on out-of-distribution samples, especially on safety-critical tasks such as healthcare, and security. However, current models heavily rely on i.i.d assumption, and are therefore sensitive to OOD data.…
Vidéo
Panel: Privacy preserving machine learning
In this panel, Microsoft’s Senior Researcher Shruti Tople will lead a discussion with prominent privacy and security researchers on the state of research in secure computation, differential privacy, and related technologies. The panel will explore…
Vidéo
Panel: Causality in search and recommendation systems
With the scale of search and recommendation, real-time robust and explainable decision-making is at the heart of search and recommendation systems that work robustly even as the user-base changes, new content appears, and topics rise…
Vidéo
Closing remarks: Responsible AI
As we’ve seen in countless media articles, AI systems can behave unfairly or unreliably. They can generate undesirable or harmful content, and they can reproduce or exacerbate existing social inequities. This track explores the complex…
Vidéo
Research talk: Maia Chess: A human-like neural network chess engine
Even when machine learning surpasses human ability in a domain, there are many reasons why AI systems that capture human-like behavior would be desirable. For example, humans may want to learn and collaborate, or humans…
Vidéo
Demo: Enabling end-to-end causal inference at scale
This session will present the two popular open-source tools for causal inference, DoWhy and EconML, developed by Microsoft Research. In this demo, researchers Amit Sharma and Eleanor Dillon will describe how the integrated toolkit (DoWhy+EconML)…
Vidéo
Research talk: Large-scale, self-supervised pretraining: From language to vision
Over the past years, large-scale pretrained models with billions of parameters have improved the state of the art in nearly every natural language processing (NLP) task. These models are fundamentally changing the research and development…
Vidéo
Technology demo: Using technology to combat human trafficking
Microsoft is a founding member of Tech Against Trafficking (TAT) – a coalition of organizations working to combat human trafficking with technology. In this session, we will introduce partnerships with the Counter Trafficking Data Collaborative…
Vidéo
Panel: Computer vision in the next decade: Deeper or broader
Deep learning plus huge training data is a popular paradigm in computer vision. However, after a decade of growth, it’s time to revisit its strengths and weaknesses. Will there be a new trend in computer…
Vidéo
Research talk: Evaluating human-like navigation in 3D video games
On the path to developing agents that learn complex human-like behavior, a key challenge is the need to quickly and accurately quantify human-likeness. While human assessments of such behavior can be highly accurate, speed and…
