Feature Attribution for Neural Network Explanation

This is a hybrid event. You can also join remotely. Please see Teams link on the seminar webpage in booking url.

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.

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.