Search Results for author: Laurent U Perrinet

Found 6 papers, 5 papers with code

Retinotopic Mapping Enhances the Robustness of Convolutional Neural Networks

no code implementations23 Feb 2024 Jean-Nicolas Jérémie, Emmanuel Daucé, Laurent U Perrinet

This study investigates whether retinotopic mapping, a critical component of foveated vision, can enhance image categorization and localization performance when integrated into deep convolutional neural networks (CNNs).

Image Categorization

Learning heterogeneous delays in a layer of spiking neurons for fast motion detection

1 code implementation26 Jul 2023 Antoine Grimaldi, Laurent U Perrinet

In this study, we present a model designed to efficiently detect temporal spiking motifs using a layer of spiking neurons equipped with heterogeneous synaptic delays.

Motion Detection

Accurate Detection of Spiking Motifs by Learning Heterogeneous Delays of a Spiking Neural Network

1 code implementation21 Jul 2023 Laurent U Perrinet

In this study, we present a novel detection model based on the inversion of a generative model of raster plot synthesis.

Ultrafast Image Categorization in Biology and Neural Models

1 code implementation7 May 2022 Jean-Nicolas Jérémie, Laurent U Perrinet

To further the comparison between biological and artificial neural networks, we re-trained the standard VGG 16 CNN on two independent tasks that are ecologically relevant to humans: detecting the presence of an animal or an artifact.

Image Categorization

Motion clouds: model-based stimulus synthesis of natural-like random textures for the study of motion perception

1 code implementation31 Aug 2012 Paula Sanz Leon, Ivo Vanzetta, Guillaume S Masson, Laurent U Perrinet

Choosing an appropriate set of stimuli is essential to characterize the response of a sensory system to a particular functional dimension, such as the eye movement following the motion of a visual scene.


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