Dendritic normalisation improves learning in sparsely connected artificial neural networks.

Artificial neural networks, taking inspiration from biological neurons, have become an invaluable tool for machine learning applications. Recent studies have developed techniques to effectively tune the connectivity of sparsely-connected artificial neural networks, which have the potential to be mor...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Alex D Bird, Peter Jedlicka, Hermann Cuntz
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/a181e8475b0a4db9adbb0ef0f836a799
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a181e8475b0a4db9adbb0ef0f836a799
record_format	dspace
spelling	oai:doaj.org-article:a181e8475b0a4db9adbb0ef0f836a7992021-12-02T19:58:07ZDendritic normalisation improves learning in sparsely connected artificial neural networks.1553-734X1553-735810.1371/journal.pcbi.1009202https://doaj.org/article/a181e8475b0a4db9adbb0ef0f836a7992021-08-01T00:00:00Zhttps://doi.org/10.1371/journal.pcbi.1009202https://doaj.org/toc/1553-734Xhttps://doaj.org/toc/1553-7358Artificial neural networks, taking inspiration from biological neurons, have become an invaluable tool for machine learning applications. Recent studies have developed techniques to effectively tune the connectivity of sparsely-connected artificial neural networks, which have the potential to be more computationally efficient than their fully-connected counterparts and more closely resemble the architectures of biological systems. We here present a normalisation, based on the biophysical behaviour of neuronal dendrites receiving distributed synaptic inputs, that divides the weight of an artificial neuron's afferent contacts by their number. We apply this dendritic normalisation to various sparsely-connected feedforward network architectures, as well as simple recurrent and self-organised networks with spatially extended units. The learning performance is significantly increased, providing an improvement over other widely-used normalisations in sparse networks. The results are two-fold, being both a practical advance in machine learning and an insight into how the structure of neuronal dendritic arbours may contribute to computation.Alex D BirdPeter JedlickaHermann CuntzPublic Library of Science (PLoS)articleBiology (General)QH301-705.5ENPLoS Computational Biology, Vol 17, Iss 8, p e1009202 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Biology (General) QH301-705.5
spellingShingle	Biology (General) QH301-705.5 Alex D Bird Peter Jedlicka Hermann Cuntz Dendritic normalisation improves learning in sparsely connected artificial neural networks.
description	Artificial neural networks, taking inspiration from biological neurons, have become an invaluable tool for machine learning applications. Recent studies have developed techniques to effectively tune the connectivity of sparsely-connected artificial neural networks, which have the potential to be more computationally efficient than their fully-connected counterparts and more closely resemble the architectures of biological systems. We here present a normalisation, based on the biophysical behaviour of neuronal dendrites receiving distributed synaptic inputs, that divides the weight of an artificial neuron's afferent contacts by their number. We apply this dendritic normalisation to various sparsely-connected feedforward network architectures, as well as simple recurrent and self-organised networks with spatially extended units. The learning performance is significantly increased, providing an improvement over other widely-used normalisations in sparse networks. The results are two-fold, being both a practical advance in machine learning and an insight into how the structure of neuronal dendritic arbours may contribute to computation.
format	article
author	Alex D Bird Peter Jedlicka Hermann Cuntz
author_facet	Alex D Bird Peter Jedlicka Hermann Cuntz
author_sort	Alex D Bird
title	Dendritic normalisation improves learning in sparsely connected artificial neural networks.
title_short	Dendritic normalisation improves learning in sparsely connected artificial neural networks.
title_full	Dendritic normalisation improves learning in sparsely connected artificial neural networks.
title_fullStr	Dendritic normalisation improves learning in sparsely connected artificial neural networks.
title_full_unstemmed	Dendritic normalisation improves learning in sparsely connected artificial neural networks.
title_sort	dendritic normalisation improves learning in sparsely connected artificial neural networks.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/a181e8475b0a4db9adbb0ef0f836a799
work_keys_str_mv	AT alexdbird dendriticnormalisationimproveslearninginsparselyconnectedartificialneuralnetworks AT peterjedlicka dendriticnormalisationimproveslearninginsparselyconnectedartificialneuralnetworks AT hermanncuntz dendriticnormalisationimproveslearninginsparselyconnectedartificialneuralnetworks
_version_	1718375792935698432

Dendritic normalisation improves learning in sparsely connected artificial neural networks.

Ejemplares similares