Fakulta matematiky, fyziky
a informatiky
Univerzita Komenského v Bratislave

Doktorandské kolokvium KAI - Štefan Pócoš (27.2.2023)

v pondelok 27.2.2023 o 13:10 hod. v miestnosti I/9

22. 02. 2023 18.24 hod.
Od: Damas Gruska

Prednášajúci: Štefan Pócoš

Názov: Explainability and Interpretability of Deep Neural Networks

Termín: 27.2.2023, 13:10 hod., I/9

It is well known that artificial neural networks (ANNs) have been shown to achieve outstanding accuracy in plenty of tasks. Although in some cases their performance is getting to its peaks, it is not the only aspect researchers are concerned about. One of the downsides of modern ANNs is their lack of explainability and interpretability. This is easily demonstrated by fooling them using adversarial examples. We examined this aspect of ANNs by applying several methods to fool them and visualized their inner behavior when fooled. We will also talk about our plan for future research, including the usage of modern networks based on attention.