21 citations · 30 across the 4 of their papers we have counts for
4 papers
Auxiliary Finite-Difference Residual-Gradient Regularization for PINNs
Stavros Kassinos
Physics-informed neural networks (PINNs) are often selected by a single scalar loss even when the quantity of interest is more specific. We study a hybrid design in which the gover…
Kourkoutas-Beta: A Sunspike-Driven Adam Optimizer with Desert Flair
Stavros C. Kassinos
Transformer neural networks are increasingly used for physics-based problems. In data-driven PDE surrogates, training samples from varying boundary and initial conditions can cause…
Core of the Magnetic Obstacle
E. V. Votyakov, S. C. Kassinos
Rich recirculation patterns have been recently discovered in the electrically conducting flow subject to a local external magnetic termed "the magnetic obstacle" [Phys. Rev. Lett.…
Analytic models of heterogenous magnetic fields for liquid metal flow simulations
E. V. Votyakov, S. C. Kassinos, X. Albets-Chico
A physically consistent approach is considered for defining an external magnetic field as needed in computational fluid dynamics problems involving magnetohydrodynamics (MHD). The…