- This event has passed.
Machine Learning Seminar: Machine learning for medical imaging and Reinforcement Learning
April 18 @ 14:15 - 16:00
We hereby wish to invite you to the third meeting in the new series of machine learning seminars. The idea is to create an informal platform where people interested in machine learning can meet and discuss across institutions and disciplines. Experienced users, newcomers, and everyone in between are welcome to participate. In this way, we can share experiences, learn from each other and maybe develop a foundation for future collaboration.
- Time: Wednesday April 18th 14:15-16:00
- Place: Haukeland Universitetssjukehus, Bikuben room «finstuen»
Agenda for third meeting:
- Alexander Selvikvåg Lundervold: Machine learning for medical imaging: opportunities, challenges and ongoing work at the MMIV
Abstract: Recent developments in machine learning (i.e. “deep learning”) have enabled a new generation of techniques in medical imaging. This will be illustrated through some of our ongoing projects at the MMIV. I’ll also discuss challenges associated with deep learning in medical imaging: e.g. the images are usually large, three-dimensional (or more), not easily labeled and can come with sometimes questionable “ground truths”. In addition, the results obtained are not always sufficiently robust and interpretable. The talk will present some ways to overcome these obstacles.
- Håkon Gimse: How to learn a machine to play Tic-tac-toe (using Reinforcement learning)
- Time for discussions and socializing.
If you are interested in giving a talk at some of the upcoming meetings, please email us at Therese.Berge.Sjursen@hvl.no
Slides from the presentations:
Slides from previous meetings can be found here.