Expressivity of Spiking Neural Networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Singh, Manjot, Fono, Adalbert, Kutyniok, Gitta
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914715149533184
author Singh, Manjot
Fono, Adalbert
Kutyniok, Gitta
author_facet Singh, Manjot
Fono, Adalbert
Kutyniok, Gitta
contents The synergy between spiking neural networks and neuromorphic hardware holds promise for the development of energy-efficient AI applications. Inspired by this potential, we revisit the foundational aspects to study the capabilities of spiking neural networks where information is encoded in the firing time of neurons. Under the Spike Response Model as a mathematical model of a spiking neuron with a linear response function, we compare the expressive power of artificial and spiking neural networks, where we initially show that they realize piecewise linear mappings. In contrast to ReLU networks, we prove that spiking neural networks can realize both continuous and discontinuous functions. Moreover, we provide complexity bounds on the size of spiking neural networks to emulate multi-layer (ReLU) neural networks. Restricting to the continuous setting, we also establish complexity bounds in the reverse direction for one-layer spiking neural networks.
format Preprint
id arxiv_https___arxiv_org_abs_2308_08218
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Expressivity of Spiking Neural Networks
Singh, Manjot
Fono, Adalbert
Kutyniok, Gitta
Neural and Evolutionary Computing
The synergy between spiking neural networks and neuromorphic hardware holds promise for the development of energy-efficient AI applications. Inspired by this potential, we revisit the foundational aspects to study the capabilities of spiking neural networks where information is encoded in the firing time of neurons. Under the Spike Response Model as a mathematical model of a spiking neuron with a linear response function, we compare the expressive power of artificial and spiking neural networks, where we initially show that they realize piecewise linear mappings. In contrast to ReLU networks, we prove that spiking neural networks can realize both continuous and discontinuous functions. Moreover, we provide complexity bounds on the size of spiking neural networks to emulate multi-layer (ReLU) neural networks. Restricting to the continuous setting, we also establish complexity bounds in the reverse direction for one-layer spiking neural networks.
title Expressivity of Spiking Neural Networks
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2308.08218