Personne
Nathanaël Perraudin
Cette personne n’est plus à l’EPFL
Publications associées (27)
espm: A Python library for the simulation of STEM-EDXS datasets
Cécile Hébert, Duncan Thomas Lindsay Alexander, Nathanaël Perraudin, Hui Chen
We present two open-source Python packages: "electron spectro-microscopy"(espm) and "electron microscopy tables"(emtables). The espm software enables the simulation of scanning transmission electron microscopy energy-dispersive X-ray spectroscopy datacubes ...
ELSEVIER2023SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators
Nathanaël Perraudin, Andreas Loukas, Karolis Martinkus
We approach the graph generation problem from a spectral perspective by first generating the dominant parts of the graph Laplacian spectrum and then building a graph matching these eigenvalues and eigenvectors. Spectral conditioning allows for direct model ...
JMLR-JOURNAL MACHINE LEARNING RESEARCH2022DeepSphere: Efficient spherical convolutional neural network with HEALPix sampling for cosmological applications
Nathanaël Perraudin, Michaël Defferrard
Convolutional Neural Networks (CNNs) are a cornerstone of the Deep Learning toolbox and have led to many breakthroughs in Artificial Intelligence. So far, these neural networks (NNs) have mostly been developed for regular Euclidean domains such as those su ...
ELSEVIER SCIENCE BV2019Stationary time-vertex signal processing
Nathanaël Perraudin, Andreas Loukas
This paper considers regression tasks involving high-dimensional multivariate processes whose structure is dependent on some known graph topology. We put forth a new definition of time-vertex wide-sense stationarity, or joint stationarity for short, that g ...
2019Global and Local Uncertainty Principles for Signals on Graphs
Pierre Vandergheynst, Nathanaël Perraudin, Benjamin Ricaud, David Shuman
Uncertainty principles such as Heisenberg's provide limits on the time-frequency concentration of a signal, and constitute an important theoretical tool for designing and evaluating linear signal transforms. Generalizations of such principles to the graph ...
2018A Time-Vertex Signal Processing Framework
Nathanaël Perraudin, Benjamin Ricaud, Andreas Loukas, Francesco Grassi
An emerging way to deal with high-dimensional non-euclidean data is to assume that the underlying structure can be captured by a graph. Recently, ideas have begun to emerge related to the analysis of time-varying graph signals. This work aims to elevate th ...
Institute of Electrical and Electronics Engineers2018Inpainting of Long Audio Segments With Similarity Graphs
We present a novel method for the compensation of long duration data loss in audio signals, in particular music. The concealment of such signal defects is based on a graph that encodes signal structure in terms of time-persistent spectral similarity. A sui ...
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2018Designing Gabor windows using convex optimization
Redundant Gabor frames admit an infinite number of dual frames, yet only the canonical dual Gabor system, constructed from the minimal l(2)-norm dual window, is widely used. This window function however, might lack desirable properties, e. g. good time-fre ...
ELSEVIER SCIENCE INC2018Graph-based structures in data science
State-of-the-art data analysis tools have to deal with high-dimensional data. Fortunately, the inherent dimensionality of data is often much smaller, as it has an internal structure limiting its degrees of freedom. In most cases, this structure can be appr ...
EPFL2017Large Scale Graph Learning from Smooth Signals
Nathanaël Perraudin, Vasilis Kalofolias
Graphs are a prevalent tool in data science, as they model the inherent structure of the data. They have been used successfully in unsupervised and semi-supervised learning. Typically they are constructed either by connecting nearest samples, or by learnin ...
2017