A VAE framework decomposes KL divergence into index-code mutual information, total correlation, and dimension-wise KL to achieve disentangled and interpretable manifold learning on unsteady fluid flows.
Annual Review of Fluid Mechanics52(Volume 52, 2020), 477–508 (2020)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.flu-dyn 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Information decomposition for disentangled and interpretable manifold learning of fluid flows via variational autoencoders
A VAE framework decomposes KL divergence into index-code mutual information, total correlation, and dimension-wise KL to achieve disentangled and interpretable manifold learning on unsteady fluid flows.