Symmetric convolutional autoencoders preserve manifold parametrization properties, yielding more accurate latent trajectories, lower reconstruction errors, and greater robustness than standard CAEs on 1D advection, Burgers, and Kuramoto-Sivashinsky test cases.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Convolutional Symmetric AutoEncoders: enhancing latent stability via differential geometry
Symmetric convolutional autoencoders preserve manifold parametrization properties, yielding more accurate latent trajectories, lower reconstruction errors, and greater robustness than standard CAEs on 1D advection, Burgers, and Kuramoto-Sivashinsky test cases.