Cargando…
Exploiting noise as a resource for computation and learning in spiking neural networks
Networks of spiking neurons underpin the extraordinary information-processing capabilities of the brain and have become pillar models in neuromorphic artificial intelligence. Despite extensive research on spiking neural networks (SNNs), most studies are established on deterministic models, overlooki...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10591140/ https://www.ncbi.nlm.nih.gov/pubmed/37876899 http://dx.doi.org/10.1016/j.patter.2023.100831 |
_version_ | 1785124160608927744 |
---|---|
author | Ma, Gehua Yan, Rui Tang, Huajin |
author_facet | Ma, Gehua Yan, Rui Tang, Huajin |
author_sort | Ma, Gehua |
collection | PubMed |
description | Networks of spiking neurons underpin the extraordinary information-processing capabilities of the brain and have become pillar models in neuromorphic artificial intelligence. Despite extensive research on spiking neural networks (SNNs), most studies are established on deterministic models, overlooking the inherent non-deterministic, noisy nature of neural computations. This study introduces the noisy SNN (NSNN) and the noise-driven learning (NDL) rule by incorporating noisy neuronal dynamics to exploit the computational advantages of noisy neural processing. The NSNN provides a theoretical framework that yields scalable, flexible, and reliable computation and learning. We demonstrate that this framework leads to spiking neural models with competitive performance, improved robustness against challenging perturbations compared with deterministic SNNs, and better reproducing probabilistic computation in neural coding. Generally, this study offers a powerful and easy-to-use tool for machine learning, neuromorphic intelligence practitioners, and computational neuroscience researchers. |
format | Online Article Text |
id | pubmed-10591140 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Elsevier |
record_format | MEDLINE/PubMed |
spelling | pubmed-105911402023-10-24 Exploiting noise as a resource for computation and learning in spiking neural networks Ma, Gehua Yan, Rui Tang, Huajin Patterns (N Y) Article Networks of spiking neurons underpin the extraordinary information-processing capabilities of the brain and have become pillar models in neuromorphic artificial intelligence. Despite extensive research on spiking neural networks (SNNs), most studies are established on deterministic models, overlooking the inherent non-deterministic, noisy nature of neural computations. This study introduces the noisy SNN (NSNN) and the noise-driven learning (NDL) rule by incorporating noisy neuronal dynamics to exploit the computational advantages of noisy neural processing. The NSNN provides a theoretical framework that yields scalable, flexible, and reliable computation and learning. We demonstrate that this framework leads to spiking neural models with competitive performance, improved robustness against challenging perturbations compared with deterministic SNNs, and better reproducing probabilistic computation in neural coding. Generally, this study offers a powerful and easy-to-use tool for machine learning, neuromorphic intelligence practitioners, and computational neuroscience researchers. Elsevier 2023-09-04 /pmc/articles/PMC10591140/ /pubmed/37876899 http://dx.doi.org/10.1016/j.patter.2023.100831 Text en © 2023 The Authors https://creativecommons.org/licenses/by/4.0/This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Ma, Gehua Yan, Rui Tang, Huajin Exploiting noise as a resource for computation and learning in spiking neural networks |
title | Exploiting noise as a resource for computation and learning in spiking neural networks |
title_full | Exploiting noise as a resource for computation and learning in spiking neural networks |
title_fullStr | Exploiting noise as a resource for computation and learning in spiking neural networks |
title_full_unstemmed | Exploiting noise as a resource for computation and learning in spiking neural networks |
title_short | Exploiting noise as a resource for computation and learning in spiking neural networks |
title_sort | exploiting noise as a resource for computation and learning in spiking neural networks |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10591140/ https://www.ncbi.nlm.nih.gov/pubmed/37876899 http://dx.doi.org/10.1016/j.patter.2023.100831 |
work_keys_str_mv | AT magehua exploitingnoiseasaresourceforcomputationandlearninginspikingneuralnetworks AT yanrui exploitingnoiseasaresourceforcomputationandlearninginspikingneuralnetworks AT tanghuajin exploitingnoiseasaresourceforcomputationandlearninginspikingneuralnetworks |