Search Results for author: Carlos Lassance

Found 15 papers, 5 papers with code

Graphs as Tools to Improve Deep Learning Methods

no code implementations8 Oct 2021 Carlos Lassance, Myriam Bontonou, Mounia Hamidouche, Bastien Pasdeloup, Lucas Drumetz, Vincent Gripon

This chapter is composed of four main parts: tools for visualizing intermediate layers in a DNN, denoising data representations, optimizing graph objective functions and regularizing the learning process.

Denoising

SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval

1 code implementation21 Sep 2021 Thibault Formal, Carlos Lassance, Benjamin Piwowarski, Stéphane Clinchant

Meanwhile, there has been a growing interest in learning \emph{sparse} representations for documents and queries, that could inherit from the desirable properties of bag-of-words models such as the exact matching of terms and the efficiency of inverted indexes.

Information Retrieval

Graphs for deep learning representations

no code implementations14 Dec 2020 Carlos Lassance

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 text translation.

Image Classification Translation

DecisiveNets: Training Deep Associative Memories to Solve Complex Machine Learning Problems

no code implementations2 Dec 2020 Vincent Gripon, Carlos Lassance, Ghouthi Boukli Hacene

Learning deep representations to solve complex machine learning tasks has become the prominent trend in the past few years.

Ranking Deep Learning Generalization using Label Variation in Latent Geometry Graphs

1 code implementation25 Nov 2020 Carlos Lassance, Louis Béthune, Myriam Bontonou, Mounia Hamidouche, Vincent Gripon

Measuring the generalization performance of a Deep Neural Network (DNN) without relying on a validation set is a difficult task.

Representing Deep Neural Networks Latent Space Geometries with Graphs

no code implementations14 Nov 2020 Carlos Lassance, Vincent Gripon, Antonio Ortega

However, when processing a batch of inputs concurrently, the corresponding set of intermediate representations exhibit relations (what we call a geometry) on which desired properties can be sought.

Graph topology inference benchmarks for machine learning

1 code implementation16 Jul 2020 Carlos Lassance, Vincent Gripon, Gonzalo Mateos

Graphs are nowadays ubiquitous in the fields of signal processing and machine learning.

Denoising General Classification

Deep geometric knowledge distillation with graphs

1 code implementation8 Nov 2019 Carlos Lassance, Myriam Bontonou, Ghouthi Boukli Hacene, Vincent Gripon, Jian Tang, Antonio Ortega

Specifically we introduce a graph-based RKD method, in which graphs are used to capture the geometry of latent spaces.

Knowledge Distillation

Improved Visual Localization via Graph Smoothing

no code implementations7 Nov 2019 Carlos Lassance, Yasir Latif, Ravi Garg, Vincent Gripon, Ian Reid

One solution to this problem is to learn a deep neural network to infer the pose of a query image after learning on a dataset of images with known poses.

Image Retrieval Visual Localization

Structural Robustness for Deep Learning Architectures

no code implementations11 Sep 2019 Carlos Lassance, Vincent Gripon, Jian Tang, Antonio Ortega

Deep Networks have been shown to provide state-of-the-art performance in many machine learning challenges.

Comparing linear structure-based and data-driven latent spatial representations for sequence prediction

no code implementations19 Aug 2019 Myriam Bontonou, Carlos Lassance, Vincent Gripon, Nicolas Farrugia

Predicting the future of Graph-supported Time Series (GTS) is a key challenge in many domains, such as climate monitoring, finance or neuroimaging.

Time Series

Attention Based Pruning for Shift Networks

1 code implementation29 May 2019 Ghouthi Boukli Hacene, Carlos Lassance, Vincent Gripon, Matthieu Courbariaux, Yoshua Bengio

In many application domains such as computer vision, Convolutional Layers (CLs) are key to the accuracy of deep learning methods.

Object Recognition

A Unified Deep Learning Formalism For Processing Graph Signals

no code implementations1 May 2019 Myriam Bontonou, Carlos Lassance, Jean-Charles Vialatte, Vincent Gripon

Convolutional Neural Networks are very efficient at processing signals defined on a discrete Euclidean space (such as images).

Cannot find the paper you are looking for? You can Submit a new open access paper.