Jan Niklas Böhm

Jan Niklas Böhm
Nik is a PhD student in the Department of Data Science at the Hertie Institute for AI in Brain Health at the University of Tübingen and the IMPRS-IS graduate school. He is interested in dimensionality reduction techniques for high-dimensional data. Learning good and compact representations in an unsupervised setting is a key part of that, some examples include contrastive learning in the form of t-SimCNE and t-SNE.
Let’s try to make sense of data by mapping it into two dimensions.
01
Böhm, J. N., Berens, P., & Kobak, D.

Unsupervised visualization of image datasets using contrastive learning

May 30, 2023 | Proceedings of the International Conference on Learning Representations (ICLR)
02
Damrich, S., Böhm, J. N., Hamprecht, F. A., & Kobak, D.

From t-SNE to UMAP with contrastive learning

May 30, 2023 | Proceedings of the International Conference on Learning Representations (ICLR)
03
Böhm, J. N., Berens, P., & Kobak, D.

Attraction-repulsion spectrum in neighbor embeddings

Feb 21, 2022 | The Journal of Machine Learning Research, 23(1), 95, 4118–4149