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.