Neural networks are widely used in numerous applications including safety-critical ones such as control and planning for autonomous systems. A central question is how to verify that they are correct with respect to some specification. Beyond correctness or robustness, we are also interested in questions such as explainability and fairness, that can in turn be specified as formal verification problems. In this course, we will see how formal methods approaches introduced in the context of program verification can be leveraged to address the verification of neural networks.
effectifs minimal / maximal:/20
Parcours de rattachement
Format des notesNumérique sur 20Littérale/grade réduit
Pour les étudiants du diplôme M2 Cyber Physical SystemLe rattrapage est autorisé (Note de rattrapage conservée)
- Crédits ECTS acquis : 2.5 ECTS
Pour les étudiants du diplôme MScT-Artificial Intelligence and Advanced Visual ComputingLe rattrapage est autorisé (Note de rattrapage conservée)
- Crédits ECTS acquis : 2 ECTS