Video Player is loading.
Current Time 0:00
Duration -:-
Loaded: 0%
Stream Type LIVE
Remaining Time 0:00
 
1x

ML model reliability from a dataset perspective

36 views
TV IJS  •  published on 18. 11. 2024 in Television
Video description
AI@JSI https://kt.ijs.si/aijsi-seminar/ Dr. Katharina Dost School of Computer Science, The University of Auckland Department of Knowledge Technologies, Jožef Stefan Institute Machine learning (ML) models depend on the data on which they are trained. Consequently, flaws in datasets can lead to significant vulnerabilities in ML models. ML practitioners frequently tend to focus on “correcting” the model without addressing the quality of the dataset. However, recognizing dataset flaws early can inform and guide subsequent data collection and improve the dataset’s overall quality. In my talk, I will advocate for this data-centric perspective. I will present my research in related areas, including selection bias identification and mitigation, applicability domains, adversarial learning, self-reinforcing bias, and active learning. Dr. Katharina Dost holds a degree in Mathematics and Computer Science from Johannes Gutenberg University of Mainz, Germany, and a PhD in Computer Science from the University of Auckland, New Zealand. Her main research interests revolve around the reliability of data and models, particularly with respect to biases, adversarial learning, and active learning. She applies her expertise to address challenges in chemistry, healthcare, and environmental science.
Visibility
Public
Language
English
Author
Institut "Jožef Stefan"
Event date
24. 10. 2024

Comments

No comments.