14 citations · 34 across the 4 of their papers we have counts for
4 papers
Activation Landscapes as a Topological Summary of Neural Network Performance
Matthew Wheeler, Jose Bouza, Peter Bubenik
We use topological data analysis (TDA) to study how data transforms as it passes through successive layers of a deep neural network (DNN). We compute the persistent homology of the…
VolterraNet: A higher order convolutional network with group equivariance for homogeneous manifolds
Monami Banerjee, Rudrasis Chakraborty, Jose Bouza +1
Convolutional neural networks have been highly successful in image-based learning tasks due to their translation equivariance property. Recent work has generalized the traditional…
MVC-Net: A Convolutional Neural Network Architecture for Manifold-Valued Images With Applications
Jose J. Bouza, Chun-Hao Yang, David Vaillancourt +1
Geometric deep learning has attracted significant attention in recent years, in part due to the availability of exotic data types for which traditional neural network architectures…
ManifoldNet: A Deep Network Framework for Manifold-valued Data
Rudrasis Chakraborty, Jose Bouza, Jonathan Manton +1
Deep neural networks have become the main work horse for many tasks involving learning from data in a variety of applications in Science and Engineering. Traditionally, the input t…