
GraphLDA: Graph Structure Priors to Improve the Accuracy in FewShot Classification
It is very common to face classification problems where the number of av...
read it

Quantization and Deployment of Deep Neural Networks on Microcontrollers
Embedding Artificial Intelligence onto lowpower devices is a challengin...
read it

Using Deep Neural Networks to Predict and Improve the Performance of Polar Codes
Polar codes can theoretically achieve very competitive Frame Error Rates...
read it

Inferring Graph Signal Translations as Invariant Transformations for Classification Tasks
The field of Graph Signal Processing (GSP) has proposed tools to general...
read it

Improving Classification Accuracy with Graph Filtering
In machine learning, classifiers are typically susceptible to noise in t...
read it

DecisiveNets: Training Deep Associative Memories to Solve Complex Machine Learning Problems
Learning deep representations to solve complex machine learning tasks ha...
read it

Ranking Deep Learning Generalization using Label Variation in Latent Geometry Graphs
Measuring the generalization performance of a Deep Neural Network (DNN) ...
read it

Continuous Pruning of Deep Convolutional Networks Using Selective Weight Decay
During the last decade, deep convolutional networks have become the refe...
read it

Representing Deep Neural Networks Latent Space Geometries with Graphs
Deep Learning (DL) has attracted a lot of attention for its ability to r...
read it

Fewshot Learning for Decoding Brain Signals
Fewshot learning consists in addressing datathrifty (inductive fewsho...
read it

Some Remarks on Replicated Simulated Annealing
Recently authors have introduced the idea of training discrete weights n...
read it

GPUbased SelfOrganizing Maps for PostLabeled FewShot Unsupervised Learning
Fewshot classification is a challenge in machine learning where the goa...
read it

ThriftyNets : Convolutional Neural Networks with Tiny Parameter Budget
Typical deep convolutional architectures present an increasing number of...
read it

Graph topology inference benchmarks for machine learning
Graphs are nowadays ubiquitous in the fields of signal processing and ma...
read it

Predicting the Accuracy of a FewShot Classifier
In the context of fewshot learning, one cannot measure the generalizati...
read it

Towards an Intrinsic Definition of Robustness for a Classifier
The robustness of classifiers has become a question of paramount importa...
read it

Leveraging the Feature Distribution in Transferbased FewShot Learning
Fewshot classification is a challenging problem due to the uncertainty ...
read it

BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization
Neural networks have demonstrably achieved stateofthe art accuracy usi...
read it

Exploiting Unsupervised Inputs for Accurate FewShot Classification
In fewshot classification, the aim is to learn models able to discrimin...
read it

Training Modern Deep Neural Networks for MemoryFault Robustness
Because deep neural networks (DNNs) rely on a large number of parameters...
read it

Efficient Hardware Implementation of Incremental Learning and Inference on Chip
In this paper, we tackle the problem of incrementally learning a classif...
read it

Deep geometric knowledge distillation with graphs
In most cases deep learning architectures are trained disregarding the a...
read it

Improved Visual Localization via Graph Smoothing
Vision based localization is the problem of inferring the pose of the ca...
read it

Structural Robustness for Deep Learning Architectures
Deep Networks have been shown to provide stateoftheart performance in...
read it

Comparing linear structurebased and datadriven latent spatial representations for sequence prediction
Predicting the future of Graphsupported Time Series (GTS) is a key chal...
read it

Attention Based Pruning for Shift Networks
In many application domains such as computer vision, Convolutional Layer...
read it

A Unified Deep Learning Formalism For Processing Graph Signals
Convolutional Neural Networks are very efficient at processing signals d...
read it

Introducing Graph Smoothness Loss for Training Deep Learning Architectures
We introduce a novel loss function for training deep learning architectu...
read it

Transfer Learning with Sparse Associative Memories
In this paper, we introduce a novel layer designed to be used as the out...
read it

Quantized Guided Pruning for Efficient Hardware Implementations of Convolutional Neural Networks
Convolutional Neural Networks (CNNs) are stateoftheart in numerous co...
read it

Transfer Incremental Learning using Data Augmentation
Deep learningbased methods have reached state of the art performances, ...
read it

Laplacian Power Networks: Bounding Indicator Function Smoothness for Adversarial Defense
Deep Neural Networks often suffer from lack of robustness to adversarial...
read it

Matching Convolutional Neural Networks without Priors about Data
We propose an extension of Convolutional Neural Networks (CNNs) to graph...
read it

Convolutional neural networks on irregular domains through approximate translations on inferred graphs
We propose a generalization of convolutional neural networks (CNNs) to i...
read it

Improving Accuracy of Nonparametric Transfer Learning via Vector Segmentation
Transfer learning using deep neural networks as feature extractors has b...
read it

Robust Associative Memories Naturally Occuring From Recurrent Hebbian Networks Under Noise
The brain is a noisy system subject to energy constraints. These facts a...
read it

Translations on graphs with neighborhood preservation
In the field of graph signal processing, defining translation operators ...
read it

Learning Local Receptive Fields and their Weight Sharing Scheme on Graphs
We propose a simple and generic layer formulation that extends the prope...
read it

Evaluating Graph Signal Processing for Neuroimaging Through Classification and Dimensionality Reduction
Graph Signal Processing (GSP) is a promising framework to analyze multi...
read it

Generalizing the Convolution Operator to extend CNNs to Irregular Domains
Convolutional Neural Networks (CNNs) have become the stateoftheart in...
read it

Towards a characterization of the uncertainty curve for graphs
Signal processing on graphs is a recent research domain that aims at gen...
read it

Compression of Deep Neural Networks on the Fly
Thanks to their stateoftheart performance, deep neural networks are i...
read it

Memory vectors for similarity search in highdimensional spaces
We study an indexing architecture to store and search in a database of h...
read it

Storing sequences in binary tournamentbased neural networks
An extension to a recently introduced architecture of cliquebased neura...
read it

Improving Sparse Associative Memories by Escaping from Bogus Fixed Points
The GriponBerrou neural network (GBNN) is a recently invented recurrent...
read it

A study of retrieval algorithms of sparse messages in networks of neural cliques
Associative memories are data structures addressed using part of the con...
read it

Storing nonuniformly distributed messages in networks of neural cliques
Associative memories are data structures that allow retrieval of stored ...
read it

A Massively Parallel Associative Memory Based on Sparse Neural Networks
Associative memories store content in such a way that the content can be...
read it

A LowPower ContentAddressableMemory Based on ClusteredSparseNetworks
A lowpower ContentAddressableMemory (CAM) is introduced employing a n...
read it

Learning sparse messages in networks of neural cliques
An extension to a recently introduced binary neural network is proposed ...
read it
Vincent Gripon
verfied profile
Permanent researcher (Chargé de recherche) at Télécom Bretagne, Postdoc at Télécom Bretagne from 20122013, Postdoc at McGill University from 20112012, PhD student at Télécom Bretagne from 20082011