Dr. Oliver Eberle
Postdoctoral Researcher
Oliver Eberle is a postdoctoral researcher working in the Machine Learning Group at Technische Universität Berlin. He received a Joint M.Sc. in Computational Neuroscience from TU/HU Berlin in 2017 and a Ph.D. degree in Machine Learning from TU Berlin in 2022.
His research focuses on explainable Artificial Intelligence (XA), Natural Language Processing, and applications to the Digital Humanities and Cognitive Science. Together with colleagues, he has worked on developing XAI methods for complex model structures, especially transformer architectures and higher-order explanations for similarity models and graph neural networks.
- Explainable AI
- Deep Learning
- Natural Language Processing
- Digital Humanities
Stephanie Brandl, Oliver Eberle, Tiago Ribeiro, Anders Søgaard, Nora Hollenstein
Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations
Thomas Schnake, Oliver Eberle, Jonas Lederer, Shinichi Nakajima, Kristof T. Schütt, Klaus-Robert Müller, Gregoire Montavon
Higher-Order Explanations of Graph Neural Networks via Relevant Walks
Hassan El-Hajj, Maryam Zamani, Jochen Büttner, Julius Martinetz, Oliver Eberle, Noga Shlomi, Anna Siebold, Grégoire Montavon, Klaus-Robert Müller, Holger Kantz & Matteo Valleriani
An Ever-Expanding Humanities Knowledge Graph: The Sphaera Corpus at the Intersection of Humanities, Data Management, and Machine Learning
Ameen Ali, Thomas Schnake, Oliver Eberle, Grégoire Montavon, Klaus-Robert Müller, Lior Wolf
XAI for Transformers: Better Explanations through Conservative Propagation
Oliver Eberle, Jochen Büttner, Florian Kräutli, Klaus-Robert Müller, Matteo Valleriani, Gregoire Montavon
Building and Interpreting Deep Similarity Models
CORALS at Tokyo Biennale 2023
CORALS is a kinetic sound sculpture by the Italian media artist Marco Barotti. The installation was created as part of the BIFOLD Artist in Residence Program and is now being exhibited at one of the largest art fairs in Asia.
Peter-Haber-Preis for AI in historical sciences
Bachelor student Anika Merklein's award-winning poster uses AI to unveil secrets of early printing.