NeuroAI & Machine Learning

Al for visual processing and energy-efficient algorithms
2026-02-03 NeuroAI & Machine Learning
Cite Slides URL
Al for visual processing and energy-efficient algorithms
A New Look for Convolutional Deep Networks
By construction, deep convolutional networks treat all pixels equally. Result: they are energy-hungry, fragile to rotations or zooms, …
2025-12-12 NeuroAI & Machine Learning
Cite MAIN Slides YouTube
A New Look for Convolutional Deep Networks
By construction, deep convolutional networks treat all pixels equally. Result: they are energy-hungry, fragile to rotations or zooms, …
2025-12-02 NeuroAI & Machine Learning
Cite URL
Mislocalization by Design: The Flash-Lag Effect as Prediction
Why do we sometimes misjudge where visual objects are? This talk explores how predictive processing may cause systematic perceptual …
2025-10-16 NeuroAI & Machine Learning
Cite Slides URL
Qu'est-ce que les Neurosciences peuvent apporter à l'Intelligence Artificielle ?
L’intelligence artificielle, plus précisément l’apprentissage profond, a fait d’énormes progrès ces dernières années. …
2025-02-14 NeuroAI & Machine Learning
Cite Slides URL
When Cortical Neurons Talk Sideways: Beyond Feedforward Visual Processing

In this seminar we will challenge the traditional understanding of neuronal connectivity in primary visual cortex. While current theory suggests that neurons connect preferentially to others with similar orientation preferences, I will present evidence for a more complex connectivity pattern based on a distance-dependent rule: short-range connections show a like-to-like bias, while long-range connections connect more widely. This revised model better explains how the visual cortex processes complex stimuli and accounts for observed variations in neuronal interactions at different scales.

2025-02-11 NeuroAI & Machine Learning
Cite Slides URL
How and why foveated retinotopy provides efficient vision
The retinas of many animals, including humans, have a specialized area of high visual acuity called the fovea, while peripheral regions …
2025-01-08 NeuroAI & Machine Learning
Cite URL
Integrating the What and Where Visual Pathways to Improve CNN Categorisation
Convolutional Neural Networks (CNNs) have been widely used for categorisation tasks over the past decades. Many studies have attempted …
PDF Cite URL HAL URL Abstract
Integrating the What and Where Visual Pathways to Improve CNN Categorisation
NeuroAI: interactions multiples entre Neurosciences et Intelligence artificielle
  • présentation de 15:50:00 à 16:20:00
2024-11-18 NeuroAI & Machine Learning
Cite Slides Conference URL
A Robust Event-Driven Approach to Always-on Object Recognition
We propose a neuromimetic architecture able to perform always-on pattern recognition. To achieve this, we extended an existing …
PDF Cite DOI Press Hal Code URL
Robots aériens agiles bio-mimetiques pour le vol en conditions réelles: Enjeux pour l'IA embarqué
2024-09-09 NeuroAI & Machine Learning
Cite Slides URL
Time-to-Contact Map by Joint Estimation of Up-to-Scale Inverse Depth and Global Motion using a Single Event Camera
Event cameras asynchronously report brightness changes with a temporal resolution in the order of microseconds, which makes them …
Cite DOI Venue Pdf Code URL
Time-to-Contact Map by Joint Estimation of Up-to-Scale Inverse Depth and Global Motion using a Single Event Camera
Learning heterogeneous delays in a layer of spiking neurons for fast motion detection
Stakes of Neuromorphic Foveation: a promising future for embedded event cameras
Cite Preprint
Learning heterogeneous delays of spiking neurons for motion detection
The response of a biological neuron depends largely on the precise timing of presynaptic spikes that reach the basal dendritic tree. …
PDF Cite DOI Venue URL
Pooling in a predictive model of V1 explains functional and structural diversity across species
Neurons in the primary visual cortex are selective to orientation with various degrees of selectivity to the spatial phase, from high …
Cite DOI URL bioRxiv
Pooling in a predictive model of V1 explains functional and structural diversity across species
Learning heterogeneous delays of spiking neurons for motion detection

Decoding spiking motifs using neurons with heterogeneous delays
The response of a biological neuron depends largely on the precise timing of presynaptic spikes that reach the basal dendritic tree. …
PDF Cite Slides Venue
Learning heterogeneous delays of Spiking Neurons for motion detection

Last updated on 2022-05-20 NeuroAI & Machine Learning
PDF Cite URL
Contributions of neuroscience to the detection and localization of objects in visual inputs
Last updated on 2022-06-16 NeuroAI & Machine Learning
Cite location
Polychrony detection using heterogeneous delays
2022-05-19 NeuroAI & Machine Learning
Cite URL
Ultra-fast categorization of images containing animals in vivo and in computo
Ultra-fast categorization of images containing animals in vivo and in computo
From event-based computations to a bio-plausible Spiking Neural Network
We propose a neuromimetic online classifier for always-on digit recognition. To achieve this, we extend an existing event-based …
PDF Cite Video Venue
A homeostatic gain control mechanism to improve event-driven object recognition
We propose a neuromimetic architecture able to perform pattern recognition. To achieve this, we extended the existing event-based …
PDF Cite DOI URL HAL Video
A robust bio-inspired approach to event-driven object recognition
We propose a neuromimetic architecture able to perform online pattern recognition. To achieve this, we extended the existing …
PDF Cite Pdf URL
Sparse Deep Predictive Coding captures contour integration capabilities of the early visual system
Both neurophysiological and psychophysical experiments have pointed out the crucial role of recurrent and feedback connections to …
PDF Cite DOI Code URL arXiv
Sparse Deep Predictive Coding captures contour integration capabilities of the early visual system
Visual search as active inference
Modelling Complex-cells and topological structure in the visual cortex of mammals using Sparse Predictive Coding
Cells in the primary visual cortex of mammals (V1) have historically been divided into two classes: simple and complex. Simple cells …
Cite URL
A dual foveal-peripheral visual processing model implements efficient saccade selection
In computer vision, the visual search task consists in extracting a scarce and specific visual information (the target) from a large …
Cite DOI Pdf Code URL bioRxiv
Modelling Complex-cells and topological structure in the visual cortex of mammals using Sparse Predictive Coding
Cells in the primary visual cortex of mammals (V1) have historically been divided into two classes: simple and complex. Simple cells …
Cite URL
Effect of top-down connections in Hierarchical Sparse Coding
Hierarchical Sparse Coding (HSC) is a powerful model to efficiently represent multi-dimensional, structured data such as images. The …
PDF Cite DOI URL arXiv
Effect of top-down connections in Hierarchical Sparse Coding
Sparse Deep Predictive Coding captures contour integration capabilities of the early visual system
Both neurophysiological and psychophysical experiments have pointed out the crucial role of recurrent and feedback connections to …
Cite URL arXiv
A hierarchical, multi-layer convolutional sparse coding algorithm based on predictive coding
Sparse coding holds the idea that signals can be concisely described as a linear mixture of few components (called atoms) picked from a …
PDF Cite URL
Modelling Complex Cells of Early Visual Cortex using Predictive Coding
Sparse Deep Predictive Coding to model visual object recognition

Sparse Deep Predictive Coding to model visual object recognition
Top-down connection in Hierarchical Sparse Coding
The brain has to solve inverse problems to correctly interpret sensory data and infer the set of causes that generated the sensory …
Cite
A low-cost, accessible eye tracking framework
Recording eye movements is a technique that attracts an increasing number of scientists, but also in the general public. Indeed, this …
Cite Pdf URL
From biological vision to unsupervised hierarchical sparse coding
The formation of connections between neural cells is essentially emerging from an unsupervised learning process. During the development …
PDF Cite URL arXiv
On the Origins of Hierarchy in Visual Processing
It is widely assumed that visual processing follows a forward sequence of processing steps along a hierarchy of laminar sub-populations …
PDF Cite URL
Selectivity to oriented patterns of different precisions
The selectivity of the visual system to oriented patterns is very well documented in a wide range of species, especially in mammals. In …
Cite Code PDF
Selectivity to oriented patterns of different precisions
Unsupervised Hierarchical Sparse Coding algorithm inspired by Biological Vision
The brain has to solve inverse problems to correctly interpret sensory data and infer the set of causes that generated the sensory …
Cite
Controlling an aerial robot with human gestures using bio-inspired algorithm
Improve performances of existing recognition computer vision algorithms with biological concepts. The gain are expected in the …
Cite
Efficient learning of sparse image representations using homeostatic regulation
One core advantage of sparse representations is the efficient coding of complex signals using compact codes. For instance, it allows …
Cite
Efficient learning of sparse image representations using homeostatic regulation
One core advantage of sparse representations is the efficient coding of complex signals using compact codes. For instance, it allows …
Cite