Pattarawat Chormai

Doctoral Candidate (deputy student representative)

Research interests: • deep learning and its interpretability • natural language processing • computational methods in sciences • knowledge acquisition and sampling-based decision-marking • data visualisation

Academic education

since 2019     Doctoral candidate, Max Planck School of Cognition, Leipzig
                         Doctoral research performed at Technische Universität Berlin, Germany
                       Supervisors: Klaus-Robert Müller & Grégoire Montavon
                         Lab rotations in the orientation phase: Simon E. Fisher, Jürgen Jost, and Klaus-Robert Müller

2015–2018 Master of Science in Data Science, Eindhoven University of Technology, the Netherlands & Technische Universität Berlin, Germany (dual degree program organized by EIT Digital Master School)

2008–2012 Bachelor of Science in Information Technology, King Mongkut's Institute of Technology, Ladkrabang, Thailand

Teaching experience

2020/2021 Machine Learning 1 & 2 (Teaching Assistant), Technische Universität Berlin, Germany

2022/2023 Deep Learning 1 (Tutor), Technische Universität Berlin, Germany

Publications

Chormai, P., Herrmann, J., Müller, K.-R., and Montavon, G. (2024). “Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces”. In: IEEE Trans. Pattern Anal. Mach. Intell. https://ieeexplore.ieee.org/document/10497845

Phatthiyaphaibun, W., Chaovavanich, K., Polpanumas, C., Suriyawongkul, A., Lowphansirikul, L., Chormai, P.,
Limkonchotiwat, P., Suntorntip, T., and Udomcharoenchaikit, C. (2023). “PyThaiNLP: Thai Natural Language
Processing in Python”. In: 3rd Workshop for Natural Language Processing Open Source Software, EMNLP.

Bender, S., Anders, C. J., Chormai, P., Marxfeld, H. A., Herrmann, J., and Montavon, G. (2023). “Towards Fixing
Clever-Hans Predictors with Counterfactual Knowledge Distillation”. In: Proceedings of the IEEE/CVF International
Conference on Computer Vision (ICCV) Workshops, pp. 2607–2615.

Chormai, P., Pu, Y., Hu, H., Fisher, S. B., Francks, C., & Kong, X.-Z. (2022). Machine learning of large-scale multimodal brain imaging data reveals neural correlates of hand preference. NeuroImage, 262, 119534. https://doi.org/10.1016/j.neuroimage.2022.119534

Chormai, P., Prasertsom, P., Cheevaprawatdomrong, J., & Rutherford, A. (2020). Syllable-based neural Thai word segmentation. In Proceedings of the 28th International Conference on Computational Linguistics, pp. 4619–4637, Barcelona, Spain (online). International Committee on Computational Linguistics. https://doi.org/10.18653/vl/2020.coling-main.407

Rieger, L., Chormai, P., Montavon, G., Hansen, L. K., & Müller, K.-R. (2018). Structuring neural networks for more explainable predictions. In H. J. Escalante et al. (Eds.), Explainable and interpretable models in computer vision and machine learning. The Springer series on challenges in machine learning (pp. 115–131). Springer: Cham, Switzerland.

Poster presentation

Chormai, P., Kong, X.-Z., Fisher, S., & Francks, C. (2021, June). Machine learning reveals multimodal MRI signatures associated with handedness [Poster]. 27th Annual Meeting of the Organization for Human Brain Mapping (OHBM), online.

Pat on Google Scholar

Pat on Github

Pat’s personal homepage

Photo: Nikolaus Brade