A PINN approach learns nearly maximal Lyapunov functions via Zubov's equation and verifies stability with SMT solvers.
Why and when can deep-but not shallow- networks avoid the curse of dimensionality: a review
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Towards Learning and Verifying Maximal Neural Lyapunov Functions
A PINN approach learns nearly maximal Lyapunov functions via Zubov's equation and verifies stability with SMT solvers.