Search Results for author: Benjamin Dees

Found 2 papers, 0 papers with code

Eigenvalues of Autoencoders in Training and at Initialization

no code implementations27 Jan 2022 Benjamin Dees, Susama Agarwala, Corey Lowman

In this paper, we investigate the evolution of autoencoders near their initialization.

Geometry and Generalization: Eigenvalues as predictors of where a network will fail to generalize

no code implementations13 Jul 2021 Susama Agarwala, Benjamin Dees, Andrew Gearhart, Corey Lowman

We study the deformation of the input space by a trained autoencoder via the Jacobians of the trained weight matrices.

Cannot find the paper you are looking for? You can Submit a new open access paper.