KATOsuper: Surrogate-accelerated neural topology optimization with sensitivity-consistent Fourier neural operators
Structural
KATOsuper presents an objective-agnostic framework that couples neural-reparameterized topology optimization with sensitivity-consistent Fourier neural operators, addressing gradient inconsistency between predicted objectives and sensitivities for stable structural optimization.
See LICENSE file Topology OptimizationFourier Neural OperatorSensitivity Analysis