Presentation
Deep networks currently have impressive performance for many common image analysis tasks, in particular when trained on large amounts of natural images. When working with complex data from applications like medicine, earth observation, or marine monitoring, we have not yet reached the potential in performance. In these areas, there is a particular need for advancing the state-of-the art in deep learning methods. The research challenges are working with limited data and labels, getting robust measures of the reliability of the network predictions, how to explain why a certain prediction is made, and to incorporate physical, geometric, or other constraints into the models. In this talk, we will present how these challenges are met in the SFI Visual Intelligence, where we work together with major important Norwegian partners in medicine, earth observation, energy imaging, and marine monitoring.
Speaker
Anne Schistad Solberg is Professor in Machine Learning and Image Analysis at the Department of Informatics, University of Oslo, and Co-Director of the SFI centre Visual Intelligence. She has worked on a broad range of machine learning applications within image analysis. Her research interests include medical imaging, earth observation, sonar imaging, seismic imaging, extraction, and machine learning.
Program
11:45 – Doors open and lunch is served
12:00 – "Learning from Image Data" by Anne H. Schistad Solberg (Professor, Research Group for Digital Signal Processing and Image Analysis)
13:00 – Mingling (and goodbye)
To participate, please fill out the registration form. This way, we will not be short on food and drinks! (Registration is not binding and you are welcome to join us anyway!)
About the seminar series
Once a month, dScience will invite you to join us for lunch, soft drinks and professional talks at the Science Library. In addition to these, we will serve lunch to PhD candidates in our lounge in Kristine Bonnevies hus every Thursday. Due to limited space (40 people), this will be first come, first served. See how to find us here (download).
Our lounge can also be booked by PhDs and Postdocs on a regular basis, whether it is for a meeting or just to hang out – we have fresh coffee all day long! Read more about the series and the upcoming program here.