Evolutionary convolutional neural networks: An application to handwriting recognition

e-Archivo Repository

Show simple item record

dc.contributor.author Baldominos Gómez, Alejandro
dc.contributor.author Sáez Achaerandio, Yago
dc.contributor.author Isasi, Pedro
dc.date.accessioned 2020-09-02T09:25:16Z
dc.date.available 2020-09-02T09:25:16Z
dc.date.issued 2018-03-29
dc.identifier.bibliographicCitation Baldominos, A., Sáez, Y., Isasi, P. (2018). Evolutionary convolutional neural networks: An application to handwriting recognition. Neurocomputing, 283, pp. 38-52
dc.identifier.issn 0925-2312
dc.identifier.uri http://hdl.handle.net/10016/30787
dc.description.abstract Convolutional neural networks (CNNs) have been used over the past years to solve many different artificial intelligence (AI) problems, providing significant advances in some domains and leading to state-of-the-art results. However, the topologies of CNNs involve many different parameters, and in most cases, their design remains a manual process that involves effort and a significant amount of trial and error. In this work, we have explored the application of neuroevolution to the automatic design of CNN topologies, introducing a common framework for this task and developing two novel solutions based on genetic algorithms and grammatical evolution. We have evaluated our proposal using the MNIST dataset for handwritten digit recognition, achieving a result that is highly competitive with the state-of-the-art without any kind of data augmentation or preprocessing. When misclassified samples are carefully observed, it is found that most of them involve handwritten digits that are difficult to recognize even by a human.
dc.description.sponsorship This research is partially supported by the Spanish Ministry of Education, Culture and Sport under FPU fellowship with identifier FPU13/03917
dc.language.iso eng
dc.publisher Elsevier
dc.rights © 2017 Elsevier B.V. All rights reserved.
dc.rights Atribución-NoComercial-SinDerivadas 3.0 España
dc.rights.uri http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subject.other Neuroevolution
dc.subject.other Evolutionary algorithms
dc.subject.other Convolutional neural networks
dc.subject.other Automatic topology design
dc.subject.other Genetic algorithms
dc.subject.other Grammatical evolution
dc.title Evolutionary convolutional neural networks: An application to handwriting recognition
dc.type article
dc.subject.eciencia Informática
dc.identifier.doi https://doi.org/10.1016/j.neucom.2017.12.049
dc.rights.accessRights openAccess
dc.relation.projectID Gobierno de España. FPU13/03917
dc.type.version acceptedVersion
dc.identifier.publicationfirstpage 38
dc.identifier.publicationlastpage 52
dc.identifier.publicationtitle NEUROCOMPUTING
dc.identifier.publicationvolume 283
dc.identifier.uxxi AR/0000021042
dc.contributor.funder Ministerio de Educación, Cultura y Deporte (España)
dc.affiliation.dpto UC3M. Departamento de Informática
dc.affiliation.grupoinv UC3M. Grupo de Investigación: Computación Evolutiva y Redes Neuronales (EVANNAI)
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)

The following license files are associated with this item:

This item appears in the following Collection(s)

Show simple item record