OxTalks will soon move to the new Halo platform and will become 'Oxford Events.' There will be a need for an OxTalks freeze. This was previously planned for Friday 14th November – a new date will be shared as soon as it is available (full details will be available on the Staff Gateway).
In the meantime, the OxTalks site will remain active and events will continue to be published.
If staff have any questions about the Oxford Events launch, please contact halo@digital.ox.ac.uk
Ashkan Khakzar is a post-doctoral research assistant at Torr vision group at the University of Oxford. His research focuses on the explainability and robustness of neural networks. He received his Ph.D. from the Technical University of Munich (TUM) in Germany.
Abstract:
This talk will explore feature attribution for interpreting vision neural networks and their black box mechanism. We will cover the main approaches to feature attribution and the cases when they could fail and when the explanations could lie. Additionally, the talk will delve into several approaches beyond attribution to provide even deeper insights into how vision neural networks operate. All concepts will be presented in an accessible and intuitive manner for a general audience.
