2024
- Set-Based Training for Neural Network Verification. arxiv, 2024 mehr… BibTeX Volltext ( DOI ) Volltext (mediaTUM)
Lukas Koller, M.Sc.
Technical University of Munich
Informatics 6 - Associate Professorship of Cyber Physical Systems (Prof. Althoff)
Postal address
Postal:
Boltzmannstr. 3
85748 Garching b. München
- Office hours: appointment by email
- lukas.koller@tum.de
Curriculum Vitae
Lukas Koller joined the Cyber-Physical-Systems Group as a Ph.D. candidate under the supervision of Prof. Dr.-Ing. Matthias Althoff in late 2023. Lukas has received both, his master's degree and his bachelor's degree in Informatics from the Technical University of Munich in 2023 and 2021, respectively.
His research interests include formal verification of neural networks and training of robust neural networks. He is a member of the DFG-funded project "Data-driven process modelling in metal forming technology".
Offered Thesis Topics
I am always looking for self-motivated students who want to work in my research area. If you are interested in writing your thesis in the field of my research, please write me an email containing your CV, transcript of records, and a rough direction you are interested in. Check the thesis proposals and practical course topics below for examples.
Ongoing:
Teaching
Practical Course – Verification, Controller Synthesis, and Design of Cyber-Physical Systems (IN2106, IN4269)
- Implementation of algorithms for formal neural network verification in CORA
Recent Topics:
Seminar – Cyber-Physical Systems (IN0014, IN2107, IN4813)
- Literature research on training robust neural networks
Recent Topics:
Lecture – Formal Methods for Cyber-Physical Systems (IN2383)