Master Thesis in Evolutionary Design of Physically Interpretable Models Leveraging Generative AI
Master Thesis in Evolutionary Design of Physically Interpretable Models Leveraging Generative AI
Employer Active
Job Alert
You will be updated with latest job alerts via email
Share
Job Alert
You will be updated with latest job alerts via email
Job Description
The design of physical models for technical processes is typically a time-consuming and effortful task particularly when physical interpretability is desired (as opposed to pure black-box modeling). Recently developed techniques that combine evolutionary algorithms with generative AI present a promising avenue for increasing the level of automation in the design of physically interpretable models.
- In your Master thesis you will review the literature on the combination of evolutionary optimization and GenAI for optimization tasks (e.g. FunSearch AlphaEvolve etc.).
- You will deepen your understanding of the various aspects and approaches to designing physical models (static models systems of differential equations).
- Additionally you will assemble a set of modeling problems of increasing difficulty to benchmark different existing approaches. This includes designing metrics to compare models against each other in terms of accuracy and complexity.
- Furthermore you will design implement and evaluate methods that combine evolutionary algorithms and generative AI for the design of physically interpretable models benchmarking them against black-box approaches and other interpretable methods (e.g. symbolic regression).
Qualifications :
- Education: Master studies in the field of Mathematics Physics Electrical Engineering Mechanical Engineering Cybernetics Computer Science or comparable
- Experience and Knowledge: proficient programming skills in Python; basic understanding of physical models particularly dynamical systems (systems of differential equations in physics electrical or mechanical engineering); background in modeling dynamical systems and machine learning preferably with experience in model evaluation (accuracy complexity generalization capabilities); background in optimization preferably with experience in evolutionary/genetic algorithms; experience in using generative AI methods (e.g. LLMs) is a plus
- Personality and Working Practice: you are highly motivated for new challenges and have a structured working style
- Languages: very good in English and basic in German
Additional Information :
Start: according to prior agreement
Duration: 6 months
Requirement for this thesis is the enrollment at university. Please attach your CV transcript of records examination regulations and if indicated a valid work and residence permit.
Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore we welcome all applications regardless of gender age disability religion ethnic origin or sexual identity.
Need further information about the job
Dr. Benjamin Hartmann (Functional Department)
49 7
#LI-DNI
Remote Work :
No
Employment Type :
Full-time
Employment Type
Full-time
