efficient coding

Retinotopy improves the categorisation and localisation of visual objects in CNNs
to be presented at the 32nd International Conference on Artificial Neural Networks (ICANN 2023) in Heraklion (Greece).
PDF Cite
Learning heterogeneous delays in a layer of spiking neurons for fast motion detection
read the paper online (paywall) or read the reprint as PDF full code with extensive Supplementary Material join the Zotero group to add and discuss more items this paper is a follow-up of Antoine Grimaldi, Camille Besnainou, Hugo Ladret, Laurent U Perrinet (2022).
PDF Cite DOI
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 URL
Ultra-Fast Image Categorization in biology and in neural models
Humans are able to robustly categorize images and can, for instance, detect the presence of an animal in a briefly flashed image in as …
Preprint Cite DOI
Ultra-Fast Image Categorization in biology and in neural models
Retinotopy improves the categorisation and localisation of visual objects in CNNs
to be presented at the Computational Cognitive Neuroscience Society Meeting 2023 in Oxford see a follow-up presentation in: Jean-Nicolas Jérémie, Emmanuel Daucé, Laurent U Perrinet (2023). Retinotopy improves the categorisation and localisation of visual objects in CNNs.
PDF Cite
Stakes of Neuromorphic Foveation: a promising future for embedded event cameras
Preprint Cite
Learning heterogeneous delays of spiking neurons for motion detection
How to efficiently make use of time in neural computations? ⏱️ With @laurentperrinet we developed a model of spiking neuron including, in addition to synaptic weights, synaptic delays. https://t.co/eztnd5CUMn Come see this work on Tuesday morning at #FENS2022 poster n° 547 🪩
PDF Cite
Ultra-rapid visual search in natural images using active deep learning
👉🏼 Jean-Nicolas Jérémie @JnJerem 📍Poster session at #FENS2022 🎯 Ultra-rapid visual search in natural images using active deep learning.#FENSAmbassador @SocNeuro_Tweets @laurentperrinet 1/2 pic.twitter.com/ldGJMCQb4c — Mélina Cordeau (@CordeauMelina) July 11, 2022 This work extends to natural scenes a previous work on visual search on a simplified task formulated in Emmanuel Daucé, Pierre Albigès, Laurent U Perrinet (2020).
PDF Cite
Ultra-rapid visual search in natural images using active deep learning
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 URL
Ultra-rapid visual search in natural images using active deep learning
Visual search, that is, the simultaneous localization and detection of a visual target of interest, is a vital task. Applied to the …
PDF Cite URL
Ultra-rapid visual search in natural images using active deep learning
Learning heterogeneous delays of Spiking Neurons for motion detection
During the #CVPR2022-#NeuroVision workshop about « What can computer vision learn from visual neuroscience? », @A_Grismaldi will talk today about « Learning hetero-synaptic delays of Spiking Neurons for motion detection » shows how to learn spike motifs !
Last updated on May 20, 2022
PDF Cite URL
Contributions of neuroscience to the detection and localization of objects in visual inputs
for visual search see: Emmanuel Daucé, Pierre Albigès, Laurent U Perrinet (2020). A dual foveal-peripheral visual processing model implements efficient saccade selection. Journal of Vision. Preprint PDF Cite Code DOI for retinotopy, see: Jean-Nicolas Jérémie, Emmanuel Daucé, Laurent U Perrinet (2022).
Last updated on Jun 16, 2022
Cite
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
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 …
Preprint PDF Cite Video DOI
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