NEURO-INSPIRED QUANTIZATION - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

NEURO-INSPIRED QUANTIZATION

Résumé

This paper presents a novel neuro-inspired quantization model which is the extension of the recently released perfect-Leaky Integrate and Fire (LIF) model. We propose that the LIF, which is a very efficient neuromathematical model that describes the spike generation neural mechanism, can lead to a groundbreaking and above all dynamic compression algorithm which is called LIF encoder/decoder. We also prove that under some assumptions, there is a link between the novel LIF encoder/decoder and the conventional Uniform Deadzone Quantizer (UDQ).
Fichier principal
Vignette du fichier
Doutsi-Neuro-inspired_Quantization-ICIP2018.pdf (125.02 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02144872 , version 1 (08-01-2021)

Identifiants

Citer

Effrosyni Doutsi, Lionel Fillatre, Marc Antonini, Julien Gaulmin. NEURO-INSPIRED QUANTIZATION. 25th IEEE International Conference on Image Processing (ICIP 2018), Oct 2018, Athènes, Greece. pp.689-693, ⟨10.1109/ICIP.2018.8451793⟩. ⟨hal-02144872⟩
66 Consultations
81 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More