dc.creator | González Díaz, Rocío | es |
dc.creator | Gutiérrez Naranjo, Miguel Ángel | es |
dc.creator | Paluzo Hidalgo, Eduardo | es |
dc.date.accessioned | 2022-07-01T11:15:28Z | |
dc.date.available | 2022-07-01T11:15:28Z | |
dc.date.issued | 2022 | |
dc.identifier.citation | González Díaz, R., Gutiérrez Naranjo, M.Á. y Paluzo Hidalgo, E. (2022). Topology-based representative datasets to reduce neural network training resources. Neural Computing and Applications, May 2022 | |
dc.identifier.issn | 1433-3058 | es |
dc.identifier.uri | https://hdl.handle.net/11441/134919 | |
dc.description.abstract | One of the main drawbacks of the practical use of neural networks is the long time required in the training process. Such a
training process consists of an iterative change of parameters trying to minimize a loss function. These changes are driven
by a dataset, which can be seen as a set of labeled points in an n-dimensional space. In this paper, we explore the concept of
a representative dataset which is a dataset smaller than the original one, satisfying a nearness condition independent of
isometric transformations. Representativeness is measured using persistence diagrams (a computational topology tool) due
to its computational efficiency. We theoretically prove that the accuracy of a perceptron evaluated on the original dataset
coincides with the accuracy of the neural network evaluated on the representative dataset when the neural network
architecture is a perceptron, the loss function is the mean squared error, and certain conditions on the representativeness of
the dataset are imposed. These theoretical results accompanied by experimentation open a door to reducing the size of the
dataset to gain time in the training process of any neural network | es |
dc.description.sponsorship | Agencia Estatal de Investigación PID2019-107339GB-100 | es |
dc.description.sponsorship | Agencia Andaluza del Conocimiento P20-01145 | es |
dc.format | application/pdf | es |
dc.format.extent | 17 | es |
dc.language.iso | eng | es |
dc.publisher | Springer | es |
dc.relation.ispartof | Neural Computing and Applications, May 2022 | |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internacional | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
dc.subject | Data reduction | es |
dc.subject | Neural networks | es |
dc.subject | Representative datasets | es |
dc.subject | Computational topology | es |
dc.title | Topology-based representative datasets to reduce neural network training resources | es |
dc.type | info:eu-repo/semantics/article | es |
dc.type.version | info:eu-repo/semantics/publishedVersion | es |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es |
dc.contributor.affiliation | Universidad de Sevilla. Departamento de Matemática Aplicada I (ETSII) | es |
dc.contributor.affiliation | Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial | es |
dc.relation.projectID | PID2019-107339GB-100 | es |
dc.relation.projectID | P20-01145 | es |
dc.relation.publisherversion | https://link.springer.com/article/10.1007/s00521-022-07252-y | es |
dc.identifier.doi | 10.1007/s00521-022-07252-y | es |
dc.contributor.group | Universidad de Sevilla. TIC193 : Computación Natural | es |
dc.contributor.group | Universidad de Sevilla. FQM-369: Combinatorial Image Analysis | es |
dc.journaltitle | Neural Computing and Applications | es |
dc.publication.issue | May 2022 | es |
dc.contributor.funder | Agencia Estatal de Investigación. España | es |
dc.contributor.funder | Agencia Andaluza del Conocimiento | es |