When is the meeting? | 15-September-2023 at 10.00 - 11.00 |
Where is the meeting? | Zoom video-conference: http://meet.nbis.se/aiaio |
What is the meeting about?AI | Research presentationOn the state of machine learning research |
Who is the responsible presenter? | Thomas Schön, Beijer Professor of AI, Dept Information Technology, UU |
Abstract: TBAPresentation: Slides In our team we aim to automate the extraction of knowledge and understanding from data. This allow for machines (and humans) to understand what is happening and to acquire new skills and learn new things. We achieve this by developing new probabilistic models and deriving algorithms capable of learnings these models from data. The systematic use of probability in representing and manipulating these models is key. It allows us to represent not only what we know, but to some extent also what we do not know. We take a particular interest in dynamical phenomena evolving over time. Besides general reflections and overview of the research area I will make use of a three explicit examples of our research with an attempt to show how new developments in machine learning can directly be used in applications. 1. Medicine - the automatic diagnosis from electrocardiograms. 2. Autonomous systems - building maps of the ambient magnetic field while using these maps for positioning. 3. Computer vision, positioning and image restoration.
Slides: TBA (after seminar)