# Spiffy: Efficient Implementation of CoLaNET for Raspberry Pi

arXiv: https://arxiv.org/abs/2506.18306 · HTML: https://mlsanity.com/paper/2506.18306/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 13 references that are in the map.
- First posted on arXiv 23 Jun 2025.

## Builds on (most cited first, 6 of 6)

- [The Hardware Lottery](https://mlsanity.com/paper/2009.06489/) (2020)
- [SoftHebb: Bayesian Inference in Unsupervised Hebbian Soft Winner-Take-All Networks](https://mlsanity.com/paper/2107.05747/) (2021)
- [Neuromorphic Artificial Intelligence Systems](https://mlsanity.com/paper/2205.13037/) (2022)
- [CoLaNET -- A Spiking Neural Network with Columnar Layered Architecture for Classification](https://mlsanity.com/paper/2409.01230/) (2024)
- [Classifying Images with CoLaNET Spiking Neural Network -- the MNIST Example](https://mlsanity.com/paper/2409.07833/) (2024)
- [A Digital Machine Learning Algorithm Simulating Spiking Neural Network CoLaNET](https://mlsanity.com/paper/2503.17111/) (2025)

## Abstract (arXiv)

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.