Výsledky vyhledávání - "Banerjee, Monami"

Report

VolterraNet: A higher order convolutional network with group equivariance for homogeneous manifolds

Autor: Banerjee, Monami, Chakraborty, Rudrasis, Bouza, Jose, Vemuri, Baba C.

Convolutional neural networks have been highly successful in image-based learning tasks due to their translation equivariance property. Recent work has generalized the traditional convolutional layer of a convolutional neural network to non-Euclidean

Externí odkaz: http://arxiv.org/abs/2106.15301

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Report

A Statistical Recurrent Model on the Manifold of Symmetric Positive Definite Matrices

Autor: Chakraborty, Rudrasis, Yang, Chun-Hao, Zhen, Xingjian, Banerjee, Monami, Archer, Derek, Vaillancourt, David, Singh, Vikas, Vemuri, Baba C.

In a number of disciplines, the data (e.g., graphs, manifolds) to be analyzed are non-Euclidean in nature. Geometric deep learning corresponds to techniques that generalize deep neural network models to such non-Euclidean spaces. Several recent paper

Externí odkaz: http://arxiv.org/abs/1805.11204

Zobrazit plný text záznamu

Report

A CNN for homogneous Riemannian manifolds with applications to Neuroimaging

Autor: Chakraborty, Rudrasis, Banerjee, Monami, Vemuri, Baba C.

Convolutional neural networks are ubiquitous in Machine Learning applications for solving a variety of problems. They however can not be used in their native form when the domain of the data is commonly encountered manifolds such as the sphere, the s

Externí odkaz: http://arxiv.org/abs/1805.05487

Zobrazit plný text záznamu

Report

Dictionary Learning and Sparse Coding on Statistical Manifolds

Autor: Chakraborty, Rudrasis, Banerjee, Monami, Vemuri, Baba C.

In this paper, we propose a novel information theoretic framework for dictionary learning (DL) and sparse coding (SC) on a statistical manifold (the manifold of probability distributions). Unlike the traditional DL and SC framework, our new formulati

Externí odkaz: http://arxiv.org/abs/1805.02505

Zobrazit plný text záznamu

Report

An information theoretic formulation of the Dictionary Learning and Sparse Coding Problems on Statistical Manifolds

Autor: Chakraborty, Rudrasis, Banerjee, Monami, Crawford, Victoria, Vemuri, Baba C.

In this work, we propose a novel information theoretic framework for dictionary learning (DL) and sparse coding (SC) on a statistical manifold (the manifold of probability distributions). Unlike the traditional DL and SC framework, our new formulatio

Externí odkaz: http://arxiv.org/abs/1604.06939

Zobrazit plný text záznamu