activity
20172025
most citedKerCNNs: biologically inspired lateral connections for classification of corrupted images

7 citations · 9 across the 5 of their papers we have counts for

collaborators

7 papers

cs.LG2025

Category learning in deep neural networks: Information content and geometry of internal representations

Laurent Bonnasse-Gahot, Jean-Pierre Nadal

In humans and other animals, category learning enhances discrimination between stimuli close to the category boundary. This phenomenon, called categorical perception, was also empi…

eess.AS2024★ 1 cited

Acoustic characterization of speech rhythm: going beyond metrics with recurrent neural networks

François Deloche, Laurent Bonnasse-Gahot, Judit Gervain

Languages have long been described according to their perceived rhythmic attributes. The associated typologies are of interest in psycholinguistics as they partly predict newborns'…

cs.LG2023

Information theoretic study of the neural geometry induced by category learning

Laurent Bonnasse-Gahot, Jean-Pierre Nadal

Categorization is an important topic both for biological and artificial neural networks. Here, we take an information theoretic approach to assess the efficiency of the representat…

cs.LG2022★ 1 cited

Interpolation, extrapolation, and local generalization in common neural networks

Laurent Bonnasse-Gahot

There has been a long history of works showing that neural networks have hard time extrapolating beyond the training set. A recent study by Balestriero et al. (2021) challenges thi…

cs.LG2020

Categorical Perception: A Groundwork for Deep Learning

Laurent Bonnasse-Gahot, Jean-Pierre Nadal

A well-known perceptual consequence of categorization in humans and other animals, called categorical perception, is notably characterized by a within-category compression and a be…

cs.CV2019★ 7 cited

KerCNNs: biologically inspired lateral connections for classification of corrupted images

Noemi Montobbio, Laurent Bonnasse-Gahot, Giovanna Citti +1

The state of the art in many computer vision tasks is represented by Convolutional Neural Networks (CNNs). Although their hierarchical organization and local feature extraction are…