Dr. rer. nat. Mattis Hartwig

- ehemaliger externer Doktorand, DFKI Mitarbeiter -

 

Institut für Informationssysteme
Universität zu Lübeck
Ratzeburger Allee 160 ( Gebäude 64 - 2.OG )
D-23562 Lübeck

Telefon: +49 451 3101 5713
Öffnet ein Fenster zum Versenden einer E-Mail E-Mail an Mattis Hartwig



Curriculum Vitae

Akademisch:

  • Oktober 2021 - today: Senior Researcher & Forschungsbereichsmanager am Deutschen Forschungszentrum für Künstliche Intelligenz
  • 06. September 2022: Promotion zum Dr. rer. nat. (Dissertationsschrift & Kolloquiumsfolien)
  • Januar 2019 - September 2022: externer Doktorand an der Univesität zu Lübeck
  • Oktober 2014 - September 2016: M. Sc. Wirtschaftsinformatik an der Universität Leipzig
  • Oktober 2014 - September 2016: M. Sc. Management an der Universität Leipzig
  • Oktober 2011- September 2014: B Sc. Wirtschaftsinformatik an der Universität Leipzig

 

Beruflich:

  • 10/2021 - today: Gründer und Geschäftsführer von singularIT GmbH
  • Januar 2017 - September 2021: Berater und Junior Projektleiter bei McKinsey & Company (since 2019 in educational leave)

Forschungsinteressen

  • Anwendungen von KI und Data Science
  • Probabilistische Graphische Modelle
  • Datensynthese
  • Cognitive Science 
  • Verknüpfung von Netz- und Symbolischen Architekturen

Publikationen

2023

  • Johanna Ott, Arthur Ledaguenel, Céline Hudelot, Mattis Hartwig: How to Think About Benchmarking Neurosymbolic AI?
    in: 17th International Workshop on Neural-Symbolic Learning and Reasoning - NESY 2023, 2023, Jul, Sienne, Italy
    Website BibTeX
  • Melle Mendikowski, Benjamin Schindler, Thomas Schmid, Ralf Möller, Mattis Hartwig: Improved Techniques for Training Tabular GANs Using Cramer s V Statistics
    in: , Proceedings of the Canadian Conference on Artificial Intelligence, 2023
    BibTeX
  • Alex Winter, Mattis Hartwig, Toralf Kirsten: Predicting Hospital Length of Stay of Patients Leaving the Emergency Department
    in: Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - HEALTHINF, 2023, p.124-131
    BibTeX
  • Nils Frohwitter, Alessa Hering, Ralf Möller, Mattis Hartwig: Evaluating the Effects of a Priori Deep Learning Image Synthesis on Multi-Modal MR-to-CT Image Registration Performance
    in: Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023), 2023, p.322-329
    BibTeX
to top

2022

  • Mattis Hartwig: New Methods for Efficient Query Answering in Gaussian Probabilistic Graphical Models
    University of Lübeck, 2022, September, PhD thesis
    BibTeX
  • Melle Mendikowski, Mattis Hartwig: Creating Customers That Never Existed: Synthesis of E-commerce Data Using CTGAN
    in: 18th International Conference on Machine Learning and Data Mining (MLDM-22), 2022, IBAI Publishing, New York, US, p.91-105
    BibTeX
  • Achim Peters, Mattis Hartwig, Tobias Spiller: Obesity and Type 2 Diabetes Mellitus Explained by the Free Energy Principle
    in: Frontiers in Psychology, 2022, Vol.13, p.931701
    BibTeX
  • Hartwig, Mattis, Bhat, Anjali, Peters, Achim: How stress can change our deepest preferences: stress habituation explained using the free energy principle
    in: Frontiers in psychology, 2022, Vol.13, p.865203
    BibTeX
  • Mareike Stender, Mattis Hartwig, Tanya Braun, Ralf Möller: Increasing State Estimation Accuracy in the Inference Algorithm on a Hybrid Factor Graph Model
    in: The 35. International FLAIRS Conference Proceedings, 2022, May
    Website BibTeX
to top

2021

  • Mattis Hartwig, Tanya Braun, Ralf Möller: Handling Overlaps When Lifting Gaussian Bayesian Networks
    in: Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI 2021), 2021, IJCAI Organization, Montreal, Kanada, p.4228-4234
    DOI BibTeX
  • Mattis Hartwig, Achim Peters: Cooperation and Social Rules Emerging From the Principle of Surprise Minimization
    in: Frontiers in Psychology, 2021, Vol.11, p.3668
    Website BibTeX
to top

2020

  • Mattis Hartwig, Ralf Möller: How to Encode Dynamic Gaussian Bayesian Networks as Gaussian Processes?
    in: AI 2020: Advances in Artificial Intelligence - 33rd Australasian Joint Conference, AI 2020, , Springer, Canberra, ACT, Australia, November 29-30, 2020, Lecture Notes in Computer Science, Vol.12576, p.371-382
    DOI BibTeX
  • Mattis Hartwig, Ralf Möller: Lifted Query Answering in Gaussian Bayesian Networks
    in: International Conference on Probabilistic Graphical Models, (PGM 2020), 23.-25. September, Aalborg, Hotel Comwell Rebild Bakker, Sk\orping, Denmark, 2020, PMLR, Proceedings of Machine Learning Research, Vol.138, p.233-244
    Website BibTeX
  • Mattis Hartwig: Efficient Query Answering in Nonparametric Probabilistic Graphical Models
    German Conference on Artificial Intelligence (Künstliche Intelligenz), 2020, Doctoral Consortium
    BibTeX
  • Marisa Mohr, Florian Wilhelm, Mattis Hartwig, Ralf Möller, Karsten Keller: New Approaches in Ordinal Pattern Representations for Multivariate Time Series
    in: Proceedings of the 33rd International Florida Artificial Intelligence Research Society Conference (FLAIRS-33), 2020, AAAI Press, North Miami Beach, Florida, USA, May 17-20, 2020, p.124-129
    DOI BibTeX
  • Mattis Hartwig, Marisa Mohr, Ralf Möller: Constructing Gaussian Processes for Probabilistic Graphical Models
    in: Proceedings of the 33rd International Florida Artificial Intelligence Research Society Conference (FLAIRS-33), 2020, AAAI, North Miami Beach, Florida, USA, May 17-20, 2020, p.57-62
    DOI BibTeX
to top

2019

  • Mattis Hartwig, Marcel Gehrke, Ralf Möller: Approximate Query Answering in Complex Gaussian Mixture Models
    in: Proceedings of the ICBK 2019, 2019, IEEE, p.81-86
    DOI BibTeX
to top