Zur JKU Startseite
{{ item.AUTOREN_ZITAT }}:
{{ item.TITEL }}{{ zitatInLang(item) }}
- Science Park 3 - Stockwerk 3 - Raum 319
- +43 732 2468 4536
- +43 732 2468 4539
- seidl(at)ml.jku.at
Brief Resume
- 2023: Research Intern, Microsoft Research Cambridge
- 2020-2024: Doctor of Science, PhD in Bioinformatics, Topic: Multimodal Contrastive Learning for Drug Discovery, IML JKU Linz
- 2019: Data Scientist, QUOMATIC.AI
- 2018: Audi AADC, Audi Autonomous Driving Cup
- 2017: Research - EEG Pilot Study, Marquette University
- 2017-2019: Master of Science, in Bioinformatics, JKU Linz
- 2014-2017: Bachelor of Science, in Medical Engineering, FH Linz
- 2013-2016: Bachelor of Science, in Information Systems, JKU Linz
Forschungsthemen
- Machine Learning for drug discovery
- Hopfield Networks
- Transformers
- Deep Learning and Neural Networks
- Few-Shot Learning
- Attention Mechanism
- Scientific Large Language Models (LLM)
- Contrastive Learning
- ML in medicine
Ausgewählte Publikationen
- Enhancing activity prediction models in drug discovery with the ability to understand human language, by, P. Seidl, A. Vall, S. Hochreiter, G. Klambauer, in International Conference on Machine Learning 2023 (ICML)
- Improving Few- and Zero-Shot Reaction Template Prediction Using Modern Hopfield Networks, by, P. Seidl, P. Renz, N. Dyubankova, P. Neves, J. Verhoeven, J. Wegner, M. Segler, S. Hochreiter, G. Klambauer, in Journal of Chemical Information and Modeling 2022 (JCIM)
- Context-enriched molecule representations improve few-shot drug discovery, by, J. Schimunek, P. Seidl, L. Friedrich, D. Kuhn, F. Rippmann, S. Hochreiter, G. Klambauer, in International Conference on Learning Representations 2023 (ICLR)
- Hopfield networks is all you need, by, H. Ramsauer, B. Schäfl, J. Lehner, P. Seidl, [and 12 others], in International Conference on Learning Representations 2021 (ICLR)
- Benchmarking recent Deep Learning methods on the extended Tox21 10k data set, by, P. Seidl, A. Mayr1, A. Vall1, S. Hochreiter, G. Klambauer, in 18th International Workshop on Quantitative Structure-Activity Relationships 2021 (QSAR)
- Using emergency department triage for machine learning-based admission and mortality prediction, by, T. Tschoellitsch, P. Seidl, C. Böck, A. Maletzky, P. Moser, S. Thumfart, M. Giretzlehner, S. Hochreiter, J. Meier, in European Journal of Emergency Medicine 2023 (EJEM)
- Supervised Machine Learning Classification for Short Straddles on the S&P500, by, A. Brunhuemer, L. Larcher, P. Seidl, S. Desmettre, J. Kofler, G. Larcher, in Risks 2022 (RISKS)
- A community effort to discover small molecule SARS-CoV-2 inhibitors, by, J. Schimunek, P. Seidl, K. Elez, [and 141 others], in Molecular Informatics 2024 (Mol. Inf.)
