Spiffy: Efficient Implementation of CoLaNET for Raspberry Pi
Andrey Derzhavin, Denis Larionov

TL;DR
This paper introduces Spiffy, a lightweight, Rust-based implementation of the CoLaNET spiking neural network architecture optimized for Raspberry Pi, achieving high accuracy and low latency without specialized hardware.
Contribution
It provides the first efficient, software-only implementation of CoLaNET for common hardware platforms, demonstrating practical SNN deployment on Raspberry Pi.
Findings
92% accuracy on MNIST
0.9 ms training latency
0.45 ms inference latency
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
