AI Seminar: XAI for representation learning

dekorativt billede

Join us for a talk by Robert Jenssen, Director of SFI Visual Intelligence and Professor at UiT The Arctic University of Norway. Everybody is welcome to attend.


XAI for representation learning  


This talk will discuss motivation for recent explainability research in deep learning, so-called XAI. The talk will briefly outline a taxonomy of present XAI methods. For a large part, XAI try to identify input features that drives supervised class predictions and have received widespread attention. These methods are mostly what we refer to as post-hoc, i.e “after-the-fact” explainability. The talk then touches upon some recent alternatives aimed to be self-explainable, i.e methods with a built-in capability for providing explanations. The main aim of the talk is however to introduce the first XAI work published for explainability in representation learning. Representation learning, e.g. by self-supervision, is crucial in a wide array of recent applications. 

Anyone can participate in the event, but please use this form to register.