A hybrid approach combining machine learning methods with physical models with preserves the physical information, while still improving the flexibility and precision of the model. This type of individually tailored hybrid approach requires a combination of strong domain knowledge and data science expertise, leading to more robust semi-interpretable models and increased physical understanding.
* Help shape the future: You are responsible for the creative and pro-active implementation of new machine learning concepts and algorithms combining data-driven and physics-based models.
* Take responsibility: Prototypical algorithm implementations and benchmarking on real-world data sets will be part of your thesis.
* Experience cooperation: Take an active role in technical discussions and creation of new ideas together with the domain experts and the machine learning research team.
* Education: Master studies in the field of machine learning, mathematics, physics, computer science, engineering or related fields with excellent grades
* Personality and Working Practice: Analytical, structured, innovative and conceptually thinking character
* Experience and Knowledge: Excellent theoretical, IT and analytical skills proven by top course grades, general knowledge of machine learning. Prior knowledge of numerical simulations and thermodynamics is a plus. Programming experience in Python and MATLAB.
* Languages: Fluent in English and good in German written and spoken
Start: according to prior agreement
Duration: 6 months
Requirement for this thesis is the enrollment at university. Please attach a motivation letter, your CV, transcript of records, examination regulations and if indicated a valid work and residence permit.
Need further information about the job?
Wael Hilali (Business Department)
+4x xxx xxx xxxx9
Videos To Watch