The structure dilemma in biological and artificial neural networks

Abstract Brain research up to date has revealed that structure and function are highly related. Thus, for example, studies have repeatedly shown that the brains of patients suffering from schizophrenia or other diseases have a different connectome compared to healthy people. Apart from stochastic pr...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Thomas Pircher, Bianca Pircher, Eberhard Schlücker, Andreas Feigenspan
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/64997af2df6745538de8d9fd4f50fe8d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:64997af2df6745538de8d9fd4f50fe8d
record_format	dspace
spelling	oai:doaj.org-article:64997af2df6745538de8d9fd4f50fe8d2021-12-02T11:37:21ZThe structure dilemma in biological and artificial neural networks10.1038/s41598-021-84813-62045-2322https://doaj.org/article/64997af2df6745538de8d9fd4f50fe8d2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-84813-6https://doaj.org/toc/2045-2322Abstract Brain research up to date has revealed that structure and function are highly related. Thus, for example, studies have repeatedly shown that the brains of patients suffering from schizophrenia or other diseases have a different connectome compared to healthy people. Apart from stochastic processes, however, an inherent logic describing how neurons connect to each other has not yet been identified. We revisited this structural dilemma by comparing and analyzing artificial and biological-based neural networks. Namely, we used feed-forward and recurrent artificial neural networks as well as networks based on the structure of the micro-connectome of C. elegans and of the human macro-connectome. We trained these diverse networks, which markedly differ in their architecture, initialization and pruning technique, and we found remarkable parallels between biological-based and artificial neural networks, as we were additionally able to show that the dilemma is also present in artificial neural networks. Our findings show that structure contains all the information, but that this structure is not exclusive. Indeed, the same structure was able to solve completely different problems with only minimal adjustments. We particularly put interest on the influence of weights and the neuron offset value, as they show a different adaption behaviour. Our findings open up new questions in the fields of artificial and biological information processing research.Thomas PircherBianca PircherEberhard SchlückerAndreas FeigenspanNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-16 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Thomas Pircher Bianca Pircher Eberhard Schlücker Andreas Feigenspan The structure dilemma in biological and artificial neural networks
description	Abstract Brain research up to date has revealed that structure and function are highly related. Thus, for example, studies have repeatedly shown that the brains of patients suffering from schizophrenia or other diseases have a different connectome compared to healthy people. Apart from stochastic processes, however, an inherent logic describing how neurons connect to each other has not yet been identified. We revisited this structural dilemma by comparing and analyzing artificial and biological-based neural networks. Namely, we used feed-forward and recurrent artificial neural networks as well as networks based on the structure of the micro-connectome of C. elegans and of the human macro-connectome. We trained these diverse networks, which markedly differ in their architecture, initialization and pruning technique, and we found remarkable parallels between biological-based and artificial neural networks, as we were additionally able to show that the dilemma is also present in artificial neural networks. Our findings show that structure contains all the information, but that this structure is not exclusive. Indeed, the same structure was able to solve completely different problems with only minimal adjustments. We particularly put interest on the influence of weights and the neuron offset value, as they show a different adaption behaviour. Our findings open up new questions in the fields of artificial and biological information processing research.
format	article
author	Thomas Pircher Bianca Pircher Eberhard Schlücker Andreas Feigenspan
author_facet	Thomas Pircher Bianca Pircher Eberhard Schlücker Andreas Feigenspan
author_sort	Thomas Pircher
title	The structure dilemma in biological and artificial neural networks
title_short	The structure dilemma in biological and artificial neural networks
title_full	The structure dilemma in biological and artificial neural networks
title_fullStr	The structure dilemma in biological and artificial neural networks
title_full_unstemmed	The structure dilemma in biological and artificial neural networks
title_sort	structure dilemma in biological and artificial neural networks
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/64997af2df6745538de8d9fd4f50fe8d
work_keys_str_mv	AT thomaspircher thestructuredilemmainbiologicalandartificialneuralnetworks AT biancapircher thestructuredilemmainbiologicalandartificialneuralnetworks AT eberhardschlucker thestructuredilemmainbiologicalandartificialneuralnetworks AT andreasfeigenspan thestructuredilemmainbiologicalandartificialneuralnetworks AT thomaspircher structuredilemmainbiologicalandartificialneuralnetworks AT biancapircher structuredilemmainbiologicalandartificialneuralnetworks AT eberhardschlucker structuredilemmainbiologicalandartificialneuralnetworks AT andreasfeigenspan structuredilemmainbiologicalandartificialneuralnetworks
_version_	1718395762562301952

The structure dilemma in biological and artificial neural networks

Ejemplares similares