Seminar/Proseminar: Explainable AI for Data Science

Explainable AI is a recent and growing subfield of machine learning (ML) that aims to bring transparency into ML models without sacrificing their predictive accuracy. This seminar will explore current research on the use of Explainable AI for extracting insights from large datasets of interest. Use cases in biomedicine, chemistry, earth sciences, and digital humanities will be covered.

Students will select a few papers from a pool of thematically relevant research papers, which they will read and present over the course of the semester.

Kick-off meeting: Friday 27 October 2023 at 14:15 in room T9/049 Seminarraum (Takustr. 9)

Information about the course: here

Presenter-Paper matching

Minh Duc Do:
 - Thomas et al. Analyzing neuroimaging data through recurrent DL models, 2019

Siyu Deng:
 - Novakovsky et al. Obtaining genetics insights from DL via XAI, 2022

Hanee Rai:
- Zednik et al. Scientific exploration and XAI, 2022

 Aditya Panchal:
 - Schütt et al. Quantum-chemical insights from interpretable atomistic NNs, 2019

 Se Yeon Kim:
 - El-Hajj et al. Explainability and transparency in the realm of digital humanities, 2023

Max Ehrlicher-Schmidt:
 - Schramowski et al. Making DNNs right for the right scientific reasons, 2020

Saniya Nankani:
 - Krenn et al. On scientific understanding with artificial intelligence, 2022

Shipra Guin:
 - Preuer et al. Interpretable deep learning in drug discovery, 2019

Cora Glaß:
 - Krenn et al. On scientific understanding with artificial intelligence, 2022

Bashar Suleiman:
 - Preuer et al. Interpretable deep learning in drug discovery, 2019

Georgi Lazarov:
 - El-Hajj et al. Explainability and transparency in the realm of digital humanities, 2023

Lukas Felmy:
 - Thomas et al. Analyzing Neuroimaging Data Through Recurrent DL Models, 2019

Nina Papenfuß:
 - Keyl et al. Patient-level proteomic network prediction by explainable AI, 2022

Anuraj Suman:
- Zednik et al. Scientific exploration and XAI, 2022