Passer à la navigation principale Passer à la recherche Passer au contenu principal

Profil personnel

Personal profile

Goran Frehse is a professor in the team Hybrid System Semantics (SSH) and serves as the director of the Computer Science and Systems Engineering department (U2IS) of ENSTA Paris.

His research focuses on the safety of cyber-physical systems, including systems driven by artificial intelligence. In particular, he is interested in the application of formal methods, coming from software analysis, to dynamical systems described by a combination of discrete events and differential equations, also referred to as hybrid systems. His research topics include:

- Modeling dynamical systems and specifying their desired behavior,
- Formally verifying dynamical systems through model-checking and reachability analysis,
- Semi-formal verification techniques such as statistical model checking,
- Monitoring and supervision of AI-based control systems,
- Verifiably safe reinforcement learning.

Research Interests

Computer Science

Intérêts de la recherche

Goran Frehse's research focuses on the safety of cyber-physical systems, including systems driven by artificial intelligence. In particular, he is interested in the application of formal methods, coming from software analysis, to dynamical systems described by a combination of discrete events and differential equations, also referred to as hybrid systems. Goran Frehse's research topics include: modeling dynamical systems and specifying their desired behavior, formally verifying dynamical systems through model-checking and reachability analysis, semi-formal verification techniques such as statistical model checking, monitoring and supervision of AI-based control systems, verifiably safe reinforcement learning.

Qualification académique

HDR (PhD Supervision Credentials)

Empreinte digitale

Passez en revue plus en détail les thèmes de recherche où Goran Frehse est actif. Ces libellés thématiques proviennent des travaux de cette personne. Ensemble, ils forment une empreinte digitale unique.
  • 1 Profils similaires

Collaborations et principaux domaines de recherche des cinq dernières années

Collaboration externe récente au niveau du pays/territoire. Voir les détails en cliquant sur les points ou