Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nguyen, Duc Anh, Araya, Ernesto, Fono, Adalbert, Kutyniok, Gitta
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911004396355584
author Nguyen, Duc Anh
Araya, Ernesto
Fono, Adalbert
Kutyniok, Gitta
author_facet Nguyen, Duc Anh
Araya, Ernesto
Fono, Adalbert
Kutyniok, Gitta
contents Recent years have seen significant progress in developing spiking neural networks (SNNs) as a potential solution to the energy challenges posed by conventional artificial neural networks (ANNs). However, our theoretical understanding of SNNs remains relatively limited compared to the ever-growing body of literature on ANNs. In this paper, we study a discrete-time model of SNNs based on leaky integrate-and-fire (LIF) neurons, referred to as discrete-time LIF-SNNs, a widely used framework that still lacks solid theoretical foundations. We demonstrate that discrete-time LIF-SNNs with static inputs and outputs realize piecewise constant functions defined on polyhedral regions, and more importantly, we quantify the network size required to approximate continuous functions. Moreover, we investigate the impact of latency (number of time steps) and depth (number of layers) on the complexity of the input space partitioning induced by discrete-time LIF-SNNs. Our analysis highlights the importance of latency and contrasts these networks with ANNs employing piecewise linear activation functions. Finally, we present numerical experiments to support our theoretical findings.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18023
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time
Nguyen, Duc Anh
Araya, Ernesto
Fono, Adalbert
Kutyniok, Gitta
Machine Learning
Neural and Evolutionary Computing
Recent years have seen significant progress in developing spiking neural networks (SNNs) as a potential solution to the energy challenges posed by conventional artificial neural networks (ANNs). However, our theoretical understanding of SNNs remains relatively limited compared to the ever-growing body of literature on ANNs. In this paper, we study a discrete-time model of SNNs based on leaky integrate-and-fire (LIF) neurons, referred to as discrete-time LIF-SNNs, a widely used framework that still lacks solid theoretical foundations. We demonstrate that discrete-time LIF-SNNs with static inputs and outputs realize piecewise constant functions defined on polyhedral regions, and more importantly, we quantify the network size required to approximate continuous functions. Moreover, we investigate the impact of latency (number of time steps) and depth (number of layers) on the complexity of the input space partitioning induced by discrete-time LIF-SNNs. Our analysis highlights the importance of latency and contrasts these networks with ANNs employing piecewise linear activation functions. Finally, we present numerical experiments to support our theoretical findings.
title Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time
topic Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2505.18023