Thesis Normalizing Flows on low dimensional Data Manifolds

Company Description

At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other. Join in and feel the difference.

The Robert Bosch GmbH is looking forward to your application!

Job Description

• Normalizing flows represent a very promising modeling choice for counterfactual analysis, mainly due to the two-way (e.g., invertible) continuous and differentiable mapping from the observation to the latent space.
• Such models, however, drastically fail due to an ill conditioned Jacobian when trying to model low dimensional data manifolds that are embedded in a higher dimensional space (see [1]).
• The objective of this thesis work is to find practical solutions addressing that limitation.

Qualifications

• Education: Master studies in the field of in Data Science, Machine Learning, Computer Science, Cybernetics, Electrical Engineering, Mathematics or comparable
• Personality and Working Practice: independent, goal-oriented, reliable and work-oriented
• Experience and Knowledge: experienced in Python or Matlab, mathematical knowledge as well as fundamental research in machine learning

Additional Information

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?
Karim Barsim (Business Department)
+49 174 3650742

Apply now in just 3 minutes!

[1]