Prof. Dr. Thomas A. Henzinger

Tom Henzinger has been President of the Institute of Science and Technology Austria (ISTA) since 2009. He received a PhD in Computer Science from Stanford University in 1991. He was Assistant Professor of Computer Science at Cornell University, Professor of Electrical Engineering and Computer Sciences at the University of California, Berkeley, Director at the Max-Planck Institute for Computer Science in Saarbrucken, and Professor of Computer and Communication Sciences at EPFL. His research focuses on developing formalisms, algorithms, and tools for the design and verification of reliable software and hardware systems. His HyTech tool was the first model checker for mixed discrete-continuous systems. He is a member of the US National Academy of Sciences, the American Academy of Arts and Sciences, Academia Europaea, the German Academy of Sciences (Leopoldina), and the Austrian Academy of Sciences. He is also a Fellow of the AAAS, the ACM, and the IEEE. He received the Robin Milner Award of the Royal Society, the EATCS Award of the European Association for Theoretical Computer Science, and the Wittgenstein Award of the Austrian Science Fund.

KEYNOTE - Formal Methods meet Neural Networks: A Selection

We review several ways in which formal methods can enhance the quality of neural networks:
first, to learn neural networks with guaranteed properties;
second, to verify properties of neural networks;
and third, to enforce properties of neural networks at runtime.
For the first topic, we discuss reinforcement learning with temporal objectives in stochastic environments; for the second, decision procedures for reasoning about quantized neural networks; for the third, monitoring learned classifiers for novelty detection and fairness, and shielding learned controllers for safety and progress.