1 code implementation • 22 Jan 2024 • Jerome Eertmans, Laurent Jacques, Claude Oestges
Recently, Differentiable Ray Tracing has been successfully applied in the field of wireless communications for learning radio materials or optimizing the transmitter orientation.
no code implementations • 10 Aug 2023 • Anatole Moureaux, Chloé Chopin, Simon de Wergifosse, Laurent Jacques, Flavio Abreu Araujo
We present a demonstration of image classification using an echo-state network (ESN) relying on a single simulated spintronic nanostructure known as the vortex-based spin-torque oscillator (STVO) delayed in time.
no code implementations • 31 Jul 2023 • Gilles Monnoyer, Thomas Feuillen, Maxime Drouguet, Laurent Jacques, Luc Vandendorpe
Our grid hopping approach, which relies on interpolation strategies, offers a reduced computation time while its performance stays on par with the direct method.
no code implementations • 27 Jul 2023 • Rémi Delogne, Vincent Schellekens, Laurent Daudet, Laurent Jacques
In this context, the possibility of performing data processing (such as pattern detection or classification) directly in the sketched domain without accessing the original data was previously achieved for linear random sketching methods and compressive sensing.
no code implementations • 17 Jul 2023 • Olivier Leblanc, Matthias Hofer, Siddharth Sivankutty, Hervé Rigneault, Laurent Jacques
Lensless illumination single-pixel imaging with a multicore fiber (MCF) is a computational imaging technique that enables potential endoscopic observations of biological samples at cellular scale.
no code implementations • 22 Jun 2023 • Olivier Leblanc, Mathias Hofer, Siddharth Sivankutty, Hervé Rigneault, Laurent Jacques
Lensless illumination single-pixel imaging with a multicore fiber (MCF) is a computational imaging technique that enables potential endoscopic observations of biological samples at cellular scale.
2 code implementations • 15 Mar 2023 • Julián Tachella, Laurent Jacques
Here we explore the extreme case of learning from binary observations and provide necessary and sufficient conditions on the number of measurements required for identifying a set of signals from incomplete binary data.
no code implementations • 16 Jan 2023 • Jérome Eertmans, Claude Oestges, Laurent Jacques
For more than twenty years, Ray Tracing methods have continued to improve on both accuracy and computational time aspects.
no code implementations • 1 Dec 2022 • Rémi Delogne, Vincent Schellekens, Laurent Daudet, Laurent Jacques
In this context, the possibility of performing data processing (such as pattern detection or classification) directly in the sketched domain without accessing the original data was previously achieved for linear random sketching methods and compressive sensing.
no code implementations • 17 May 2022 • Rémi Delogne, Vincent Schellekens, Laurent Jacques
In a nutshell, the SPE shows that the scalar product of a signal sketch with the "sign" of the sketch of a given pattern approximates the square of the projection of that signal on this pattern.
no code implementations • NeurIPS 2023 • Sjoerd Dirksen, Martin Genzel, Laurent Jacques, Alexander Stollenwerk
Neural networks with random weights appear in a variety of machine learning applications, most prominently as the initialization of many deep learning algorithms and as a computationally cheap alternative to fully learned neural networks.
no code implementations • 22 Apr 2021 • Stéphanie Guérit, Siddharth Sivankutty, John Aldo Lee, Hervé Rigneault, Laurent Jacques
We develop our approach on two key properties of the LE: (i) the ability to easily generate speckles, and (ii) the memory effect in MCF that allows to use fast scan mirrors to shift light patterns.
no code implementations • 20 Apr 2021 • Vincent Schellekens, Laurent Jacques
The compressive learning framework reduces the computational cost of training on large-scale datasets.
no code implementations • 9 Feb 2021 • Gilles Monnoyer de Galland, Thomas Feuillen, Luc Vandendorpe, Laurent Jacques
This algorithm extends existing continuous greedy algorithms to the framework of factorized sparse representations of the signals.
no code implementations • 29 Jan 2021 • Benoît Pairet, Faustine Cantalloube, Laurent Jacques
However, the faint intensity of the circumstellar disks compared to the brightness of the host star compels astronomers to use tailored observation strategies, in addition to state-of-the-art optical devices.
Instrumentation and Methods for Astrophysics Earth and Planetary Astrophysics Information Theory Information Theory
no code implementations • 10 Nov 2020 • Gilles Monnoyer de Galland, Thomas Feuillen, Luc Vandendorpe, Laurent Jacques
In this paper we propose to bridge the gap between using extremely low resolution 1-bit measurements and estimating targets' parameters, such as their velocities, that exist in a continuum, i. e., by performing Off-the-Grid estimation.
no code implementations • 14 Sep 2020 • Vincent Schellekens, Laurent Jacques
In compressive learning, a mixture model (a set of centroids or a Gaussian mixture) is learned from a sketch vector, that serves as a highly compressed representation of the dataset.
no code implementations • 17 Aug 2020 • Thomas Feuillen, Mike Davies, Luc Vandendorpe, Laurent Jacques
This work focuses on the reconstruction of sparse signals from their 1-bit measurements.
no code implementations • 4 Aug 2020 • Rémi Gribonval, Antoine Chatalic, Nicolas Keriven, Vincent Schellekens, Laurent Jacques, Philip Schniter
This article considers "compressive learning," an approach to large-scale machine learning where datasets are massively compressed before learning (e. g., clustering, classification, or regression) is performed.
no code implementations • 2 Jul 2020 • Gilles Monnoyer de Galland, Luc Vandendorpe, Laurent Jacques
We propose a fast greedy algorithm to compute sparse representations of signals from continuous dictionaries that are factorizable, i. e., with atoms that can be separated as a product of sub-atoms.
no code implementations • 14 Apr 2020 • Vincent Schellekens, Laurent Jacques
Concretely, we introduce the general framework of asymmetric random periodic features, where the two signals of interest are observed through random periodic features: random projections followed by a general periodic map, which is allowed to be different for both signals.
1 code implementation • 12 Feb 2020 • Vincent Schellekens, Laurent Jacques
Generative networks implicitly approximate complex densities from their sampling with impressive accuracy.
no code implementations • 4 Dec 2018 • Vincent Schellekens, Laurent Jacques
Compressive learning is a framework where (so far unsupervised) learning tasks use not the entire dataset but a compressed summary (sketch) of it.
no code implementations • 3 Dec 2018 • Sandrine Anthoine, Yannick Boursier, Laurent Jacques
The iTWIST workshop series aim at fostering collaboration between international scientific teams for developing new theories, applications and generalizations of low-complexity models.
no code implementations • 31 Oct 2018 • Amirafshar Moshtaghpour, José M. Bioucas-Dias, Laurent Jacques
Single Pixel (SP) imaging is now a reality in many applications, e. g., biomedical ultrathin endoscope and fluorescent spectroscopy.
no code implementations • 29 Oct 2018 • Stéphanie Guérit, Siddharth Sivankutty, Camille Scotté, John Alto Lee, Hervé Rigneault, Laurent Jacques
The lensless endoscope is a promising device designed to image tissues in vivo at the cellular scale.
no code implementations • 4 Sep 2018 • Amirafshar Moshtaghpour, José M. Bioucas-Dias, Laurent Jacques
This paper introduces a single-pixel HyperSpectral (HS) imaging framework based on Fourier Transform Interferometry (FTI).
no code implementations • 26 Apr 2018 • Vincent Schellekens, Laurent Jacques
The recent framework of compressive statistical learning aims at designing tractable learning algorithms that use only a heavily compressed representation-or sketch-of massive datasets.
no code implementations • 6 Feb 2018 • Kévin Degraux, Valerio Cambareri, Bert Geelen, Laurent Jacques, Gauthier Lafruit
This paper introduces two acquisition device architectures for multispectral compressive imaging.
no code implementations • NeurIPS 2016 • Kévin Degraux, Gabriel Peyré, Jalal Fadili, Laurent Jacques
More precisely, we focus in detail on the cases of $\ell_1$ and $\ell_\infty$ losses, and contrast them with the usual $\ell_2$ loss. While these losses are routinely used to account for either sparse ($\ell_1$ loss) or uniform ($\ell_\infty$ loss) noise models, a theoretical analysis of their performance is still lacking.
no code implementations • 5 Aug 2016 • Stéphanie Guérit, Adriana González, Anne Bol, John A. Lee, Laurent Jacques
Images from positron emission tomography (PET) provide metabolic information about the human body.
no code implementations • 18 Feb 2016 • Adriana Gonzalez, Hong Jiang, Gang Huang, Laurent Jacques
We consider the problem of reconstructing an image from compressive measurements using a multi-resolution grid.
no code implementations • 17 Feb 2016 • Arnaud Browet, Christophe De Vleeschouwer, Laurent Jacques, Navrita Mathiah, Bechara Saykali, Isabelle Migeotte
To isolate individual cells in live imaging data, we introduce an elegant image segmentation framework that effectively extracts cell boundaries, even in the presence of poor edge details.
no code implementations • 16 Jun 2015 • Stéphanie Guérit, Laurent Jacques, Benoît Macq, John A. Lee
Improving the quality of positron emission tomography (PET) images, affected by low resolution and high level of noise, is a challenging task in nuclear medicine and radiotherapy.
no code implementations • 5 Apr 2015 • Amit Kumar K. C., Laurent Jacques, Christophe De Vleeschouwer
Given a set of detections, detected at each time instant independently, we investigate how to associate them across time.
no code implementations • 19 Dec 2014 • Adriana Gonzalez, Véronique Delouille, Laurent Jacques
Contrarily to most methods presented in the literature, our method does not assume a parametric model of the PSF and can thus be applied to any telescope.
no code implementations • 25 Jun 2014 • Prasad Sudhakar, Laurent Jacques, Xavier Dubois, Philippe Antoine, Luc Joannes
This compressive characterization is then confirmed with experimental results on simple plano-convex and multifocal intra-ocular lenses studying the evolution of the main deflection as a function of the object point location.
no code implementations • 4 Sep 2012 • Adriana Gonzalez, Laurent Jacques, Christophe De Vleeschouwer, Philippe Antoine
Optical Deflectometric Tomography (ODT) provides an accurate characterization of transparent materials whose complex surfaces present a real challenge for manufacture and control.