Members
Members are listed in chronological order of joining the lab.
![Bastian Rieck](br.jpg)
Bastian Rieck
Principal Investigator
Principal Investigator
- GitHub
- Pseudomanifold
- ORCID
- 0000-0003-4335-0302
- @Pseudomanifold
- Web
- https://bastian.rieck.me
When it comes to machine learning, Bastian is interested in
all things geometrical and topological, with a particularly
strong focus on biomedical applications.
![Julius von Rohrscheidt](jvr.jpg)
Julius von Rohrscheidt
Ph.D. Student
Ph.D. Student
- @JRohrscheidt
- Web
- https://rohrscheidt.com
Julius is particularly interested in the development and investigation of
robust topological representation learning procedures.
This includes the construction of new feature extraction algorithms,
as well as the investigation of limitations and performance of these techniques.
![Jeremy Wayland](jw.jpg)
Jeremy Wayland
Ph.D. Student
Ph.D. Student
- GitHub
- jeremy-wayland
- ORCID
- 0000-0002-8766-8737
- @jeremy_wayland
- Web
- https://jeremy-wayland.me
Jeremy is interested developing practical and usable topology-based methods for improving our
understanding of various generative models. Additionally,
he enjoys applying topological methods in collaborative projects that focus on predictive medicine and/or climate change.
![Katharina Limbeck](kl.jpg)
Katharina Limbeck
Ph.D. Student
Ph.D. Student
- GitHub
- LimbeckKat
- @LimbeckKat
- Web
- https://limbeckkat.github.io/
Katharina is interested in using and developing topological machine learning methods
to analyse complex structures in biomedical data, in particular single cell data.
![Ernst Röell](er.jpg)
Ernst Röell
Ph.D. Student
Ph.D. Student
Ernst is interested in building scalable topological
descriptors that can be used as machine learning layers.
Furthermore, he is interested in the application of abstract algebra and
sheaves to understand data structures and machine learning
algorithms.
![Salome Kazeminia](sk.jpg)
Salome Kazeminia
Ph.D. Student
Ph.D. Student
- @KazeminiaSalome
Salome is interested in unsupervised, self-supervised, and weakly supervised deep models,
focusing on trustworthy representation and manifold learning to advance AI in health applications.
![Sebastian Birk](sb.jpg)
![Franz Srambical](fs.jpg)
Franz Srambical
Research Assistant
Research Assistant
- GitHub
- emergenz
- @lemergenz
- Web
- https://srambical.fr
Franz is interested in leveraging known
topological/physical constraints to solve problems in the natural
sciences, including – but not limited to – the realm of drug
discovery. He is also interested in representation learning for EEG data.
![Pragya Singh](ps.jpg)
Pragya Singh
M.Sc. Student
M.Sc. Student
- GitHub
- pragyasingh7
Pragya is an incoming MSc student at Imperial College London. She
is interested in geometrical and topological machine learnng, especially
its application in natural sciences.
![Pia Baronetzky](pb.jpg)
Pia Baronetzky
M.Sc. Student
M.Sc. Student
- GitHub
- peppey
Pia is a Mathematics master student at TUM. She is interested in Machine
Learning und Topological Data Analysis, and in how Data Science can be
applied to solve meaningful problems.
![Katharina Hagedorn](kh.jpg)
Katharina Hagedorn
B.Sc. Student
B.Sc. Student
- GitHub
- KatharinaHagedorn
Katharina is doing her bachelor’s thesis in computer science
at TUM. She is interested in machine learning approaches in
biomedicine and healthcare, especially in the field of
antimicrobial resistance prediction.
![Irene Cannistraci](ic.jpg)
Irene Cannistraci
Visiting Researcher
Visiting Researcher
- @ire_cannistraci
- Web
- https://irene.cannistraci.dev
Irene is interested in studying and analyzing how and why independent
neural networks encode information similarly. This includes leveraging
geometrical and topological techniques to manipulate the latent space
and enable the adaptation and reutilization of different neural models.
![Rubén Ballester](rb.jpg)
Rubén Ballester
Ph.D. Student
Ph.D. Student
- GitHub
- rballeba
- ORCID
- 0000-0001-8172-6652
- @rballeba
- Web
- https://rubenbb.com
Rubén is interested in developing the foundations of
topological and categorical deep learning models. On the
topological side, Rubén enjoys working with models that
leverage the topological and combinatorial structures
of the input. On the categorical side, Rubén is especially
interested in studying the fundamental blocks
of deep learning by means of category theory and in
developing logic and symbolic neural networks backed by
categorical methods.
Collaborators
![]() Adrien Aumon |
![]() Davide Buffelli |
![]() Corinna Coupette |
![]() Sebastian Dalleiger |
![]() Leon Hetzel |
![]() Alexandros Keros |
Your name is missing here! Learn more about joining us.
Alumni & Alumnae
- Marek Cerny (now a Ph.D. student with Floris Geerts at the University of Antwerp)
- Ferdinand Hölzl (now a master’s student at University of Hamburg)
- Barış Onarıcı
- Tejas Srinivasan
- Kalyan Varma Nadimpalli (now a research assistant at IIT Madras)