4 papers
Geometric instability of out of distribution data across autoencoder architecture
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 dif…
Eigenvalues of Autoencoders in Training and at Initialization
Benjamin Dees, Susama Agarwala, Corey Lowman
In this paper, we investigate the evolution of autoencoders near their initialization. In particular, we study the distribution of the eigenvalues of the Jacobian matrices of autoe…
Instructive artificial intelligence (AI) for human training, assistance, and explainability
Nicholas Kantack, Nina Cohen, Nathan Bos +3
We propose a novel approach to explainable AI (XAI) based on the concept of "instruction" from neural networks. In this case study, we demonstrate how a superhuman neural network m…
Geometry and Generalization: Eigenvalues as predictors of where a network will fail to generalize
Susama Agarwala, Benjamin Dees, Andrew Gearhart +1
We study the deformation of the input space by a trained autoencoder via the Jacobians of the trained weight matrices. In doing so, we prove bounds for the mean squared errors for…