Florian P. Mahner

I am a PhD Candidate at the Max Planck Research Group Vision and Computational Cognition supervised by Martin Hebart. I am also a guest researcher at the Neural Coding Lab and co-supervised by Umut Güçlü.

Research Interests

My work primarily focuses on representation learning in humans and machines. I combine computational modeling and machine learning with insights from cognitive science to understand the similarities and differences between human and artificial systems. I mostly work on vision, but also use insights from language and other domains. I am particularly interested in interpretable alignment of representations and how to use insights from cognitive science to improve machine learning models and vice versa.

I am working on a couple of projects on the intersection of these fields. If you are interested in collaborating, feel free to reach out.

Academic Background

PhD in Machine Learning, 2021-2025
Max Planck Research Group Vision and Computational Cognition
Supervisors: Martin Hebart, Umut Güçlü

MSc in Artificial Intelligence, 2018-2021
Radboud University
Grade: Excellent with distinction, top 1%
Thesis: Neural Decoding with Normalizing Flows

BSc in Cognitive Science, 2013-2017
Osnabrück University
Grade: Excellent
Thesis: View-independent human motion analysis of eigensubspace and temporal self-similarity representations

Selected Publications

arXiv

Dimensions underlying the representational alignment of deep neural networks with humans

Florian P Mahner, Lukas Muttenthaler, Umut Güçlü, and Martin N Hebart

arXiv preprint arXiv:2406.19087, 2024

Bib PDF

@article{mahner2024dimensions,
  title = {Dimensions underlying the representational alignment of deep neural networks with humans},
  author = {Mahner, Florian P and Muttenthaler, Lukas and G{\"u}{\c{c}}l{\"u}, Umut and Hebart, Martin N},
  journal = {arXiv preprint arXiv:2406.19087},
  year = {2024},
}