Spiffy: Efficient Implementation of CoLaNET for Raspberry Pi

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Derzhavin, Andrey, Larionov, Denis
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915355056668672
author Derzhavin, Andrey
Larionov, Denis
author_facet Derzhavin, Andrey
Larionov, Denis
contents This paper presents a lightweight software-based approach for running spiking neural networks (SNNs) without relying on specialized neuromorphic hardware or frameworks. Instead, we implement a specific SNN architecture (CoLaNET) in Rust and optimize it for common computing platforms. As a case study, we demonstrate our implementation, called Spiffy, on a Raspberry Pi using the MNIST dataset. Spiffy achieves 92% accuracy with low latency - just 0.9 ms per training step and 0.45 ms per inference step. The code is open-source.
format Preprint
id arxiv_https___arxiv_org_abs_2506_18306
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Spiffy: Efficient Implementation of CoLaNET for Raspberry Pi
Derzhavin, Andrey
Larionov, Denis
Neural and Evolutionary Computing
Artificial Intelligence
This paper presents a lightweight software-based approach for running spiking neural networks (SNNs) without relying on specialized neuromorphic hardware or frameworks. Instead, we implement a specific SNN architecture (CoLaNET) in Rust and optimize it for common computing platforms. As a case study, we demonstrate our implementation, called Spiffy, on a Raspberry Pi using the MNIST dataset. Spiffy achieves 92% accuracy with low latency - just 0.9 ms per training step and 0.45 ms per inference step. The code is open-source.
title Spiffy: Efficient Implementation of CoLaNET for Raspberry Pi
topic Neural and Evolutionary Computing
Artificial Intelligence
url https://arxiv.org/abs/2506.18306