no code implementations • 19 Oct 2021 • 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).
1 code implementation • 5 Jun 2021 • Monami Banerjee, Rudrasis Chakraborty, Jose Bouza, Baba C. Vemuri
In this paper, we present a novel higher order Volterra convolutional neural network (VolterraNet) for data defined as samples of functions on Riemannian homogeneous spaces.
no code implementations • ICLR 2019 • Rudrasis Chakraborty, Jose Bouza, Jonathan Manton, Baba C. Vemuri
To this end, we present a provably convergent recursive computation of the wFM of the given data, where the weights makeup the convolution mask, to be learned.
1 code implementation • 11 Sep 2018 • Rudrasis Chakraborty, Jose Bouza, Jonathan Manton, Baba C. Vemuri
Thus, there is need to generalize the deep neural networks to cope with input data that reside on curved manifolds where vector space operations are not naturally admissible.