# Quantization in Spiking Neural Networks

arXiv: https://arxiv.org/abs/2305.08012 · HTML: https://mlsanity.com/paper/2305.08012/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 10 references that are in the map.
- First posted on arXiv 13 May 2023.

## Builds on (most cited first, 3 of 3)

- [Training Spiking Neural Networks Using Lessons From Deep Learning](https://mlsanity.com/paper/2109.12894/) (2021)
- [On Quasi-Isometry of Threshold-Based Sampling](https://mlsanity.com/paper/1811.01436/) (2018)
- [Spiking Neural Networks in the Alexiewicz Topology: A New Perspective on Analysis and Error Bounds](https://mlsanity.com/paper/2305.05772/) (2023)

## Abstract (arXiv)

In spiking neural networks (SNN), at each node, an incoming sequence of weighted Dirac pulses is converted into an output sequence of weighted Dirac pulses by a leaky-integrate-and-fire (LIF) neuron model based on spike aggregation and thresholding. We show that this mapping can be understood as a quantization operator and state a corresponding formula for the quantization error by means of the Alexiewicz norm. This analysis has implications for rethinking re-initialization in the LIF model, leading to the proposal of 'reset-to-mod' as a modulo-based reset variant.