Sicco Verwer

Sicco Verwer is an Associate Professor in machine learning with applications in cyber security and software engineering at TU Delft since 2014. Before this, he has been a postdoctoral researcher for several years at RU Nijmegen, KU Leuven, and TU Eindhoven.
He has worked on several topics in machine learning and is best known for his work in grammatical inference, i.e., learning state machines from trace data. He has researched and implemented several algorithms for learning such models including RTI, which is one of the first that is able to learn timed automata. In 2013, he received a VENI grant from STW to extend this work and apply it in cyber security. Other recent work include several methods for declarative modelling of machine learning problems using mathematical solvers, and making classifiers discrimination-aware.
He teaches two courses in the cyber security master at TU Delft: Cyber Data Analytics and Automated Software Testing and Reverse Engineering.
If you are interested in the research performed by his lab, or joining as PhD or MSc student, please have a look at Sicco's publications and past publicly available MSc and BSc theses.

  1. Sicco Verwer, Yingqian Zhang, Learning optimal classification trees using a binary linear program formulation, In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence Volume 33 p.1625-1632, Association for the Advancement of Artificial Intelligence (AAAI).
  2. Yihuan Zhang, Qin Lin, Jun Wang, Sicco Verwer, John M. Dolan, A data-driven behavior generation algorithm in car-following scenarios, In Dynamics of Vehicles on Roads and Tracks Volume 1 p.1-2, CRC Press.
  3. Sicco Verwer, Menno van Zaanen, Rick Smetsers, Proceedings of the 13th International Conference on Grammatical Inference ICGI: JMLR Workshop and Conference Proceedings
  4. MJH Heule, SE Verwer, Using a satisfiability solver to identify deterministic finite state automata, In BNAIC 2009 Benelux Conference on Artificial Intelligence p.91-98, BNAIC.
  5. R Smetsers, M Volpato, FW Vaandrager, SE Verwer, Bigger is not always better: on the quality of hypotheses in active automata learning, In Proceedings of the 12th International Conference of Grammatical Inference p.167-181.
  6. MJH Heule, SE Verwer, Exact DFA Identification Using SAT Solvers, In Grammatical Inference: Theoretical Results and Applications 10th International Colloquium, ICGI 2010 p.66-79, Springer.
  7. SE Verwer, MM de Weerdt, C Witteveen, Identifying an automaton model for timed data (extended abstract), In Proceedings of the Belgium-Dutch Conference on Artificial Intelligence (BNAIC) p.439-440, BNVKI.
  8. SE Verwer, MM de Weerdt, C Witteveen, Identifying an automaton model for timed data, In Proceedings of the Annual Machine Learning Conference of Belgium and the Netherlands (Benelearn) p.57-64, Benelearn.
  9. SE Verwer, MM de Weerdt, C Witteveen, Efficiently learning timed models from observations, In Benelearn 2008 p.75-76, Universite de Liege.
  10. SE Verwer, MM de Weerdt, C Witteveen, On the identifiability in the limit of timed automata, In Proceedings of the Grammatical inference workshop on open problems and new directions p.-.

Dr. S.E. Verwer