Show simple item record

dc.contributor.authorAlaíz Gudin, Carlos María es_ES
dc.contributor.authorFernández Pascual, Ángela es_ES
dc.contributor.authorDorronsoro Ibero, José Ramón es_ES
dc.contributor.editorBruges : i6doc.comen_US
dc.contributor.otherUAM. Departamento de Ingeniería Informáticaes_ES
dc.date.accessioned2022-07-15T07:29:49Zen_US
dc.date.available2022-07-15T07:29:49Zen_US
dc.date.issued2020-10-04en_US
dc.identifier.citationESANN 2020 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Online event, 2-4 October 2020, i6doc.com publ., 169-174en_US
dc.identifier.isbn9782875870742es_ES
dc.identifier.urihttp://hdl.handle.net/10486/703125en_US
dc.description.abstractVisualization of a learning machine can be crucial to understand its behaviour, specially in the case of (deep) neural networks, since they are quite difficult to interpret. An approach for visualizing the feature space of a neural network is presented, trying to answer to the question “what representation of the data is the network using to make its decision?” The proposed method gives a representation of the space where the network is tackling the problem, reducing it while respecting the linearity of the model. As shown experimentally, this technique allows to study the evolution of the model with respect to the training epochs, to have a representation of the data similar to the one used by the neural network, and even to detect groups of patterns that behave differentlyen_US
dc.description.sponsorshipWith partial support from the European Regional Development Fund and from the Spanish Ministry of Economy, Industry, and Competitiveness, project TIN2016-76406-P (AEI/FEDER, UE). Work supported also by UAM–ADIC Chair for Data Science and Machine Learning. We also acknowledge the use of the facilities of Centro de Computacion Cientıfica (CCC) at UAMen_US
dc.format.extent6 pag.en_US
dc.format.mimetypeapplication/pdfen_US
dc.language.isoengen_US
dc.publisher© ESANN 2020en_US
dc.relation.ispartofEuropean Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learningen_US
dc.rightsCopyright © ESANN, 2020en_US
dc.titleVisualization of the Feature Space of Neural Networksen_US
dc.typebookParten_US
dc.typeconferenceObjecten_US
dc.subject.ecienciaInformáticaes_ES
dc.identifier.publicationfirstpage169es_ES
dc.identifier.publicationlastpage174es_ES
dc.relation.projectIDGobierno de España. TIN2016-76406-Pes_ES
dc.type.versioninfo:eu-repo/semantics/publishedVersionen_US
dc.rights.accessRightsopenAccessen_US
dc.facultadUAMEscuela Politécnica Superiores_ES


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record