ATW-SNN: low-accuracy-loss asymmetric ternary-weight spiking neural network with spike calibration strategy

The deployment of spiking neural networks (SNNs) on resource-constrained devices is mainly limited by memory footprint and energy consumption. Specifically, these limitations stem from the overhead incurred by full-precision storage and floating-point operations. To address these bottlenecks, we pro...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Yihang Chen, Haoran Gao, Yingcheng Lin, Cong Shi
Formato:	Artigo
Idioma:	Inglês
Publicado em:	IOP Publishing 2026-01-01
Colecção:	Neuromorphic Computing and Engineering
Assuntos:	spiking neural network (SNN) ternary weights model compression asymmetric quantization knowledge distillation
Acesso em linha:	https://doi.org/10.1088/2634-4386/ae379b
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!