[DMANET] PhD Position in Formal Methods and Machine Learning at TU Delft

PhD Position in Formal Methods and Machine Learning at TU Delft

Challenge: Reliability of systems controlled by neural networks. Change: Synergy between formal methods and machine learning. Impact: Novel formal methods for guaranteeing properties of neural-network controlled systems.

The main difference between offline verification and real-time monitoring of learned controllers, such as neural networks or deep reinforcement learning, is to identify when we can no longer guarantee verified system behavior and to repair guarantees. The challenge of this project is to develop scalable approaches for formally monitoring AI systems and adapting to the real-time changes.

You will conduct both theoretical and empirical research on real-time monitoring and verification of AI under the real-world uncertainties. We envision the project to have significant scientific impact in the intersection of formal methods and machine learning.

You will be part of the Algorithmics Group in the Department of Software Technology of the Faculty of Electrical Engineering, Mathematics and Computer Science. As a PhD researcher, you will reinforce and extend the group's expertise in the interdisciplinary field combining formal methods and machine learning. You will work in a dynamic and diverse environment of other PhD and postdoc researchers excited about making theoretical and algorithmic contributions in intelligent decision making.

Apply until June 11, 2023: https://www.academictransfer.com/en/327675/phd-position-in-formal-methods-and-machine-learning/
**********************************************************
*
* Contributions to be spread via DMANET are submitted to
*
* DMANET@zpr.uni-koeln.de
*
* Replies to a message carried on DMANET should NOT be
* addressed to DMANET but to the original sender. The
* original sender, however, is invited to prepare an
* update of the replies received and to communicate it
* via DMANET.
*
* DISCRETE MATHEMATICS AND ALGORITHMS NETWORK (DMANET)
* http://www.zaik.uni-koeln.de/AFS/publications/dmanet/
*
**********************************************************