no code implementations • 27 Jul 2022 • C. Chace Ashcraft, Benjamin Stoler, Chigozie Ewulum, Susama Agarwala
Transfer learning is an increasingly common approach for developing performant RL agents.
no code implementations • 28 Jan 2022 • Susama Agarwala, Ben Dees, Corey Lowman
We study the map learned by a family of autoencoders trained on MNIST, and evaluated on ten different data sets created by the random selection of pixel values according to ten different distributions.
no code implementations • 27 Jan 2022 • Benjamin Dees, Susama Agarwala, Corey Lowman
In this paper, we investigate the evolution of autoencoders near their initialization.
no code implementations • 13 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.