Formal Methods for Machine Learning

This course will cover several topics at the intersection of formal methods and machine learning, for instance, abstraction refinement for analyzing deep neural networks, algorithms for reliable learning-based control, interpretable model design, and formal methods for verification and monitoring of learned systems. The course should be useful for students of both formal methods and machine learning, and lies at the intersection of these areas. Since the area is relatively new, the course material will be primarily based on research papers.

The final grade of the course consists of the following components:

• Participation (weighting 15%)

• Presenting Papers (weighting 15%)

• Final Report (weighting 70%)

Final grade calculation = 0.15 * Participation + 0.15 * Presenting Papers + 0.7 * Final report

A passing final grade for the course can only be earned when for all components at least a 5.0 is earned, and the weighted final grade is at least a 5.8.

In case of an insufficient final result, repair options may exist in accordance with Article 17A, Times and number of examinations, sub 1, of the Teaching and Examination Regulations, for:

• Participation: No repair opportunity

• Presenting Papers: resit

• Final report: re-submit deliverable

Disclaimer: information may change depending on unforeseen circumstances or measures (see: TER Art 2, sub 5).