CV
General Information
Name: Lukas Paul Achatius Galke
Address: Campusvej 55, 5230 Odense, Denmark
Office: Ø12-509b-2
Experience
2024–present: Assistant Professor, University of Southern Denmark (SDU), Department of Mathematics and Computer Science (IMADA), Section for Data Science and Statistics (DSS), Centre for Machine Learning (C4ML)
2022-2024: Postdoctoral Researcher, Max Planck Institute for Psycholinguistics
2017-2022: Doctoral Researcher, Kiel University & ZBW
Education
2022: PhD in Computer Science, Kiel University, Germany
2017: M.Sc. in Computer Science, Kiel University, Germany
2013: BSc in Computer Science, Kiel University, Germany
Teaching experience as main lecturer
2025, Spring: Advanced Machine Learning, SDU
2024, Autumn: Deep Learning, SDU
Selected publications
- Galke, L., Ram, Y., Raviv, L. (2024) Deep neural networks and humans both benefit from compositional language structure. Nature Communications 15:10816.
- Galke, L., Vagliano, I., Franke, B., Zielke, T., Hoffmann, M., Scherp A. (2023). Lifelong Learning on Evolving Graphs Under the Constraints of Imbalanced Classes and New Classes. Neural Networks 164, 156-176.
- Galke, L., Scherp, A. (2022). Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP. ACL 2022, pages 4038–4051.
Selected invited talks
- Emergent communication and learning pressures in language models. Workshop on Using Artificial Neural Networks for Studying Human Language Learning and Processing, 2024, June 10, University of Amsterdam.
- Lifelong Learning and Out-of-distribution Detection on Evolving Graphs. VU AI Colloquium, 2023, July 10, Vrije Universiteit Amsterdam, Netherlands.
- What makes a language easy to deep-learn? Computational Linguistics Seminar, 2023, May 16, University of Amsterdam, Netherlands.
Academic service
- Program Committee: ACL, CogSci, CIKM, ECAI, EMNLP, ICLR
- Reviewer: Artificial Intelligence Review, IEEE Access, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Knowledge and Data Engineering, Information Processing and Management, Journal of Artificial Intelligence Reseearch, Journal of Web Semantics, Knowledge-based Systems, Nature Communications, Nature Scientific Reports, Neural Networks, Pattern Recognition
Contact: lukas 'at' lpag.de
Design: Adapted from Diane Mounter.
Privacy: No personal data, no cookies.