English

Spiffy: Efficient Implementation of CoLaNET for Raspberry Pi

Neural and Evolutionary Computing 2025-06-24 v1 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2506.18306,
  title  = {Spiffy: Efficient Implementation of CoLaNET for Raspberry Pi},
  author = {Andrey Derzhavin and Denis Larionov},
  journal= {arXiv preprint arXiv:2506.18306},
  year   = {2025}
}

Comments

7 pages, 3 figures

R2 v1 2026-07-01T03:28:52.096Z