Michael Biehl, Groningen, Machine Learning, Intelligent Systems, Neural Networks, Artificial Intelligence, Computer Science,

home mini-CV research publications teaching PhD students student projects talks/tutorials code memberships
RUG-page legal notice

Any vacancies, available internships etc. will be announced properly through the usual channels and on this website.
Unsolicited applications for internships, PhD or PostDoc positions etc. will probably remain unanswered.

Michael Biehl, University of Groningen

Full Professor in Machine Learning, Theory and Applications

Michael Biehl, book cover, The Shallow and the Deep

University of Groningen, Bernoulli Institute for Mathematics,
Computer Science and Artificial Intelligence,
Computer Science Department, Intelligent Systems Group

Nijenborgh 9, 9747 AG Groningen, NL m dot biehl at rug dot nl
Room 5161.0584 Tel +31 50 363 3997 meikelbiehl at gmail dot com

Honorary Professor of Machine Learning, University of Birmingham
Center for Systems Modelling and Quantitative Biomedicine

+++ new +++ list of publications (pdf and bibtex, including links)

Research:
Machine Learning and Computational Intelligence
          Theory and algorithm development for neural networks
          Learning Vector Quantization and Relevance Learning
          Applications in life sciences, biomedical data, astroinformatics
Statistical Physics and Scientific Computing
          Theory of neural networks, dynamics of machine learning processes
          Monte Carlo simulations of complex systems
          Disordered systems, non-equilibrium growth processes

Teaching:
Neural Networks and Computational Intelligence
Modelling and Simulation
Introduction to Machine Learning

+++ +++ breaking news +++ +++

April 2026:
More than 8000 downloads (UGP and PURE) of
"The Shallow and the Deep" since its open access publication end of September 2023.

March 2026:
The final version of the Nature Machine Intelligence paper
Aligning generalization between humans and machines
is now publically available at pure.rug.nl

Just published (online, open access) in Neurocomputing:
FA(IR)^2MA-GMLVQ - A hidden-feature-bias mitigation approach for fairness in classification learning base on generalized matrix learning vector quantization
by M Kaden, R Schubert, J Voigt, L Reuss, A Engelsberger, S Lövdal, E van den Brandhof, M Biehl, T Villmann

January 2026:
Accepted for publication and oral presentation at ESANN 2026 in Bruges/Belgium (22-24 April):
Autoencoders versus PCA for feature extraction in FDG PET scans in neurodegenerative diseases
by Roland Veen, Sofie Lövdal (joint first authors), Kaitlin Vos, Ciro Setolino, Sanne Meles and Michael Biehl.

January 2026:
Just published (online, open access) in eBioMedicine:
Endocrine and metabolic determinants of cardiometabolic risk in mild autonomous cortisol secretion
A collaborative project led by Wiebke Arlt (MRC Lab London) and Alessandro Prete (U of Birmingham), with important
contributions from thesis projects by Ariadna Albors-Zumel, Elina van den Brandhof, Yuanqing Zhang and Ludger Visser.

December 2025:
Our publication
Iterated Relevance Matrix Analysis for improved classification and robustness in prototype-based learning schemes
with joint first authors Sofie Lövdal and Elina van den Brandhof
is available at Neurocomputing

Any vacancies, available internships, etc. will be announced properly through the usual channels and on this website.
Unsolicited applications for internships, PhD or PostDoc positions etc. will probably remain unanswered.