AI Research Group at the University of Tübingen


Neuro AI – Autonomous Lifelong Learning in Machines and Brains

Our lab works on “Neuro AI” – the interface between machine learning and computational neuroscience. We both develop ML tools for neural data analysis and take inspiration from the brain about what key problems to solve in ML and also how to tackle them. The brain excels in autonomous learning from unlabeled data streams. While machine learning is rapidly advancing toward learning with unlabeled or weakly labeled datasets, autonomous knowledge accumulation through continuous data collection is largely missing. To address this discrepancy, we develop mathematical concepts, build machine learning systems, and compare machines to brains in terms of their representational structure and learning algorithms. Our previous research on these topics can be summarized under the following headings:

Representation learning for compression, disentangling, and o.o.d. robustness

Lifelong learning requires making experiences in the past reusable for the future. Representations of these experiences need to be memory efficient (compressed) and compositional (disentangled) to facilitate reliable one-shot generalization to new situations that cannot be regarded as samples from a known distribution (Out-of-distribution robustness).

Probabilistic inference and o.o.d. or few-shot generalization benchmarking

Benchmarking is a fundamental tool for evaluating the ability of an ML algorithm to generalize from previous experience to new situations. The academic standard concept of training and testing with samples from the same distribution does not capture the robustness of biological learning systems acting in an open world. We frequently work on benchmarks to improve the comparability of models and avoid shortcut learning.

Generative and explainable modeling methods

Discriminative methods learn to map data to labels but different models with identical i.i.d. test performance may use completely different features for decision making. This can be demonstrated e.g. by the use of carefully designed architectures that exclude the use of certain features. In addition, we use generative methods such as adversarial, controversial, or style transfer stimuli that can help to reveal the features used by a neural network, or that are used during inference (analysis-by-synthesis). Sometimes these methods also facilitate aesthetically compelling image manipulations similar to artistic styles.

Behavioral data analysis, modeling, and tools

We collect and use behavioral data to predict where people look and what features they use for visual decision making and memorization. We also built tools for tracking lifelong natural behavior such as keypoint extraction. We collaborate with Felix Wichmann, Alexander Mathis, Ralf Engbert, and Christoph Teufel.

Neural data analysis, modeling, and tools

We develop machine learning models for neural data analysis to identify the function of biological neurons for inference and learning in the brain (mostly mammalian retina and visual cortex). We are particularly interested in understanding distributed processing in populations of neurons and building tools for automatic model extraction such as functional cell type identification. We collaborate with Thomas Euler, Andreas Tolias and Mackenzie Mathis.

AI sciencepreneurship and startups

Machine learning is rapidly expanding the range of skills that can be used for new solutions to relevant problems in the world either by being more scalable or more precise then human labor. We seek to develop a better understanding of how we can develop economically feasible solutions that best address long-term human needs. We spin off and collaborate with startups such as Maddox AI, Vara, or Aleph Alpha.


Two Day Lab Hackathon 2023
Innovative research, collaboration, and fun are at the core of our lab’s mission. At our recent two-day hackathon we explored cutting-edge ideas on group actions, object-centric learning, and stable diffusion.
Two Day Lab Hackathon 2023
Bethgelab ❤️ ELLIS
Bethgelab is part of ELLIS - the European Laboratory for Learning and Intelligent Systems
Bethgelab ❤️ ELLIS

Broader Impact

Impact Beyond Science


The Bundeswettbewerb für Künstliche Intelligenz (BWKI) is a federal competition for artificial intelligence (AI) in Germany, Austria and recently Switzerland. It is organized by the Tübingen AI Center funded by the Carl-Zeiss-Stiftung and is aimed at promoting interest and talent in AI among young people. The competition is open to students from different age groups, and participants work in teams to develop innovative solutions for real-world problems using AI technologies. The BWKI also aims to encourage the development of AI skills and knowledge, which is becoming increasingly important in today’s digital age.


IT4Kids is a non-profit organization in Germany that provides programming education for primary and lower secondary school students. Their mission is to support the digital transformation of education in schools by teaching coding and programming skills to children in a fun and engaging way.