Graph Laplacians for Rotation Equivariant Convolutional Neural Networks
M Milani - 2019 - infoscience.epfl.ch
A fundamental problem in signal processing is to design computationally efficient algorithms
to filter signals. In many applications, the signals to filter lie on a sphere. Meaningful …
to filter signals. In many applications, the signals to filter lie on a sphere. Meaningful …
Identification of spatial communities in the human genome graph to better understand HIV latency and insertion
R García Gutiérrez - 2019 - upcommons.upc.edu
In this work, the 3D spatial organization of a human Jurkat cell, an immune cell who is one
ofthe main targets of the human immunodeficiency virus (HIV), is analyzed through the …
ofthe main targets of the human immunodeficiency virus (HIV), is analyzed through the …
Graphs for deep learning representations
C Lassance - arXiv preprint arXiv:2012.07439, 2020 - arxiv.org
In recent years, Deep Learning methods have achieved state of the art performance in a vast
range of machine learning tasks, including image classification and multilingual automatic …
range of machine learning tasks, including image classification and multilingual automatic …
Graph Laplacians on the sphere for rotation equivariant neural networks
M MILANI - 2018 - politesi.polimi.it
A fundamental problem in signal processing is to design computationally efficient algorithms
to filter signals. In many applications, the signals to filter lie on a sphere. Meaningful …
to filter signals. In many applications, the signals to filter lie on a sphere. Meaningful …