World's Best Scientists 2026 revealed!
Thomas Villmann

Thomas Villmann

D-Index & Metrics

Computer Science

D-Index
36
Citations
6530
World Ranking
11140
National Ranking
558

Overview

Thomas Villmann is affiliated with Hochschule Mittweida in Germany and has made contributions primarily in the fields of Computer Science and Biochemistry, Genetics and Molecular Biology. Their research focuses extensively on Artificial Intelligence and Molecular Biology, with additional work in Computer Vision and Pattern Recognition, Control and Systems Engineering, and Computational Theory and Mathematics.

The scientist's main topics of work concentrate on Neural Networks and Applications, Machine Learning in Bioinformatics, Adversarial Robustness in Machine Learning, Machine Learning and Data Classification, Fractal and DNA sequence analysis, Anomaly Detection Techniques and Applications, and Fault Detection and Control Systems.

Frequent publication venues include:

  • Neurocomputing
  • ESANN 2021 proceedings
  • Neural Computing and Applications
  • Entropy
  • bioRxiv (Cold Spring Harbor Laboratory)

Several recent papers illustrate their research outputs, such as:

  • "The coming of age of interpretable and explainable machine learning models" (2023) published in Neurocomputing
  • "Alignment-Free Sequence Comparison: A Systematic Survey From a Machine Learning Perspective" (2022) published in IEEE/ACM Transactions on Computational Biology and Bioinformatics
  • "The Coming of Age of Interpretable and Explainable Machine Learning Models" (2021) published in ESANN 2021 proceedings
  • "Learning vector quantization as an interpretable classifier for the detection of SARS-CoV-2 types based on their RNA sequences" (2021) published in Neural Computing and Applications
  • "Variants of DropConnect in Learning vector quantization networks for evaluation of classification stability" (2020) published in Neurocomputing

Thomas Villmann collaborates frequently with several coauthors, including Marika Kaden, Sascha Saralajew, Katrin Sophie Bohnsack, Jensun Ravichandran, and Alexander Engelsberger. These collaborations have contributed to a consistent output of publications in key venues within their fields of study.

Best Publications

  • Generalized relevance learning vector quantization

    Barbara Hammer;Thomas Villmann

  • Topology preservation in self-organizing feature maps: exact definition and measurement

    T. Villmann;R. Der;M. Herrmann;T.M. Martinetz

  • Neural maps in remote sensing image analysis

    Thomas Villmann;Erzsébet Merényi;Barbara Hammer

  • Serotonin and dopamine transporter imaging in patients with obsessive-compulsive disorder.

    Swen Hesse;Ulrich Müller;Ulrich Müller;Thomas Lincke;Henryk Barthel

  • Growing a hypercubical output space in a self-organizing feature map

    H.-U. Bauer;T. Villmann

  • Supervised Neural Gas with General Similarity Measure

    Barbara Hammer;Marc Strickert;Thomas Villmann

  • Batch and median neural gas

    Marie Cottrell;Barbara Hammer;Alexander Hasenfuß;Thomas Villmann

  • Prototype-based models in machine learning.

    Michael Biehl;Barbara Hammer;Thomas Villmann

  • Neural maps and topographic vector quantization

    H.-U. Bauer;M. Herrmann;T. Villmann

  • Limited Rank Matrix Learning, discriminative dimension reduction and visualization

    Kerstin Bunte;Petra Schneider;Barbara Hammer;Frank-Michael Schleif

  • Vector Quantization by Optimal Neural Gas

    M. Herrmann;Thomas Villmann

  • Regularization in Matrix Relevance Learning

    Petra Schneider;Kerstin Bunte;Han Stiekema;Barbara Hammer

  • Stochastic neighbor embedding (SNE) for dimension reduction and visualization using arbitrary divergences

    Kerstin Bunte;Sven Haase;Michael Biehl;Thomas Villmann

  • On the Generalization Ability of GRLVQ Networks

    Barbara Hammer;Marc Strickert;Thomas Villmann

  • Divergence-based vector quantization

    Thomas Villmann;Sven Haase

  • Magnification Control in Self-Organizing Maps and Neural Gas

    Thomas Villmann;Jens Christian Claussen

  • Computational aspects of inverse analyses for determining softening curves of concrete

    Volker Slowik;Beate Villmann;Nick Bretschneider;Thomas Villmann

  • Divergence-based classification in learning vector quantization

    E. Mwebaze;P. Schneider;F. M. Schleif;J. R. Aduwo

  • Aspects in Classification Learning - Review of Recent Developments in Learning Vector Quantization

    M. Kaden;M. Lange;D. Nebel;M. Riedel

  • Can Learning Vector Quantization be an Alternative to SVM and Deep Learning? - Recent Trends and Advanced Variants of Learning Vector Quantization for Classification Learning

    Thomas Villmann;Andrea Bohnsack;Marika Kaden

Frequent Co-Authors

Barbara Hammer
Barbara Hammer Bielefeld University
Jacek Blazewicz
Jacek Blazewicz Poznań University of Technology
Michel Verleysen
Michel Verleysen Université Catholique de Louvain
Axel Wismüller
Axel Wismüller University of Rochester
Henryk Barthel
Henryk Barthel Leipzig University
Thomas Martinetz
Thomas Martinetz University of Lübeck
Sepp Hochreiter
Sepp Hochreiter Johannes Kepler University of Linz
Nese Sreenivasulu
Nese Sreenivasulu International Rice Research Institute
Andreas Zell
Andreas Zell University of Tübingen
Alessandro Sperduti
Alessandro Sperduti University of Padua

External Links

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring computer science doesn't mean you have to follow the traditional, on-campus route. There are many flexible paths, including pursuing an online associate's degree in computer science or a related field. This option is ideal if you're just starting out or prefer a quicker, cost-effective entry into tech.

Cost is a major consideration for many students. Choosing one of the most affordable online colleges can help you earn your degree without overwhelming student debt.

Worried about your academic background? There are many online graduate schools with low gpa requirements that can help you continue your education and advance your career, even if your undergraduate grades weren’t perfect.

In addition to computer science, some degrees like environmental science also offer excellent prospects. You may be interested in the variety of high-paying jobs with environmental science degree if you want a multidisciplinary career blending technology, science, and sustainability.

Best Scientists Citing Thomas Villmann

Trending Scientists

Recently Published Articles