Running summarizing tools on a new article

Check the paper below, then start its synthesis.


Oracle-Preserving Latent Flows

Alexander Roman, Roy T. Forestano, Konstantin T. Matchev, Katia Matcheva, Eyup B. Unlu

9 pages, 8 figures
License: CC BY 4.0

Abstract: We develop a deep learning methodology for the simultaneous discovery of multiple nontrivial continuous symmetries across an entire labelled dataset. The symmetry transformations and the corresponding generators are modeled with fully connected neural networks trained with a specially constructed loss function ensuring the desired symmetry properties. The two new elements in this work are the use of a reduced-dimensionality latent space and the generalization to transformations invariant with respect to high-dimensional oracles. The method is demonstrated with several examples on the MNIST digit dataset.

Submitted to arXiv on 02 Feb. 2023