Learning hetero-synaptic delays for motion detection in a single layer of spiking neurons - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Learning hetero-synaptic delays for motion detection in a single layer of spiking neurons

Résumé

The response of a biological neuron depends on the precise timing of afferent spikes. This temporal aspect of the neuronal code is essential in understanding information processing in neurobiology and applies particularly well to the output of neuromorphic hardware such as event-based cameras. However, most artificial neuronal models do not take advantage of this minute temporal dimension and here, we develop a model for the efficient detection of temporal spiking motifs based on a layer of neurons with hetero-synaptic delays. Indeed, the variety of synaptic delays on the dendritic tree allows to synchronize synaptic inputs as they reach the basal dendritic tree. We show this can be formalized as a time-invariant logistic regression which can be trained using labelled data. We apply this model to solve the specific computer vision problem of motion detection, and demonstrate its application to synthetic naturalistic videos transformed into event streams similar to the output of event-based cameras. In particular, we quantify how its accuracy can vary with the total computational load. This end-to-end event-driven computational brick could help improve the performance of future Spiking Neural Network (SNN) algorithms and their prospective use in neuromorphic chips.
Fichier principal
Vignette du fichier
2022-07-11_Grimaldi-etal-ICIP.pdf (699.13 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03934188 , version 1 (11-01-2023)

Identifiants

Citer

Antoine Grimaldi, Laurent U Perrinet. Learning hetero-synaptic delays for motion detection in a single layer of spiking neurons. IEEE International Conference on Image Processing (ICIP), Oct 2022, Bordeaux, France. pp.3591-3595, ⟨10.1109/ICIP46576.2022.9897394⟩. ⟨hal-03934188⟩
11 Consultations
49 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More