Mostrar el registro sencillo del ítem

dc.contributor.authorPuerto, E
dc.contributor.authorAguilar, J
dc.contributor.authorReyes, J
dc.contributor.authorSarkar, D
dc.date.accessioned2021-12-02T15:03:42Z
dc.date.available2021-12-02T15:03:42Z
dc.date.issued2018-12-07
dc.identifier.urihttp://repositorio.ufps.edu.co/handle/ufps/1651
dc.description.abstractIn this work, we propose a deep learning approach for the recursive pattern recognition model, called AR2P (for its acronym in Spanish: "Algoritmo Recursivo de Reconocimiento de Patrones"), by extending its supervised learning capability towards a semi-supervised learning scheme. The deep learning architecture is composed of three phases: the first one, called discovery phase, discovers the atomic descriptors. The second one, called aggregation phase, creates a feature hierarchy (merge of descriptors) from atomic descriptors. Finally, the classification phase carries out the classification of the inputs based on the feature hierarchy. The last phase uses a supervised learning approach, while the first two follow an unsupervised learning approach. In this paper is tested the performance of the proposed model, using a dataset from the UCI Machine Learning Repository.eng
dc.format.extent08 páginasspa
dc.format.mimetypeapplication/pdfspa
dc.language.isoengspa
dc.publisherJournal of Physics: Conference Seriesspa
dc.relation.ispartofJournal of Physics: Conference Series
dc.rights© Copyright 2021 IOP Publishingeng
dc.sourcehttps://iopscience.iop.org/article/10.1088/1742-6596/1126/1/012035/metaspa
dc.titleDeep learning architecture for the recursive patterns recognition modeleng
dc.typeArtículo de revistaspa
dcterms.referencesLeCun Y, Bengio Y and Hinton G 2015 Deep learning Nature 521 436spa
dcterms.referencesSchmidhuber J 2015 Deep learning in neural networks: An overview Neural networks 61 85-117spa
dcterms.referencesLeCun Y and Bengio Y 1995 The Handbook of Brain Theory and Neural Networks ed Michael A. Arbib (Massachusetts: MIT Press Cambridge) Convolutional networks for images, speech, and time series 255-258spa
dcterms.referencesSalakhutdinov R and Hinton G 2009 Proc. Intl Conference on Artificial Intelligence and Statistics ed David van Dyk and Max Welling (Florida USA: Journal of Machine Learning Research) Deep boltzmann machines 448-455spa
dcterms.referencesHua Y, Guo J and Hua Z. 2015 Proceedings of International Conference on Intelligent Computing and Internet of Things (Harbin, China: IEEE) Deep belief networks and deep learning 1-4spa
dcterms.referencesSenior A, Sak H and Shafran I 2015 Proceedings International Conference on Acoustics, Speech and Signal Processing (ICASSP) (Brisbane, QLD, Australia: IEEE) Context dependent phone models for LSTM RNN acoustic modelling 4585-4589spa
dcterms.referencesPuerto E and Aguilar J 2017 Un algoritmo recursivo de reconocimiento de patrones Revista Técnica de la Facultad de Ingeniería Universidad del Zulia 40 95-104spa
dcterms.referencesPuerto E, Aguilar J and Chavez D 2017 A New Recursive Patterns Matching Model Inspired in Systematic Theory of Human Mind International Journal of Advancements in Computing Technology (IJACT) 9 28-39spa
dcterms.referencesPuerto E and Aguilar J 2016 Proceedings Latin American Conference on Computational Intelligence (Cartagena, Colombia: IEEE) Formal description of a pattern for a recursive process of recognition 1-2spa
dcterms.referencesPuerto E and Aguilar J 2016 Learning algorithm for the recursive pattern recognition model Appl. Artif. Intell 30 662-678spa
dcterms.referencesPuerto E, Aguilar J and Perez B 2014 Proc. Congreso Internacional en Innovación y Apropiación de las Tecnologías de la Información y las Comunicaciones (Bucaramanga, Colombia: UNAB) Análisis de la teoría de la Mmnte humana basada en el reconocimiento de patrones cap. 21spa
dcterms.referencesKurzweil R 2013 How to make mind: Can Nonbiological Brains Have Real Minds of Their Own? The Futurist 47 14-17spa
dcterms.referencesPuerto E, Aguilar J and Chávez D 2018 A recursive patterns matching model for the dynamic pattern recognition problem Appl. Artif. Intell. 32 419-432spa
dcterms.referencesAguilar J 2001 Learning algorithm and retrieval process for the multiple classes random neural network model Neural Processing Letters 13 81-91spa
dcterms.referencesAguilar J 1998 Definition of an energy function for the random neural to solve optimization problems Neural Networks 11 731-737spa
dcterms.referencesPham D, Dimov S and Nguyen C 2005 Selection of K in K-means clustering Proc. Inst. Mech. Eng. 219 103-119spa
dcterms.referencesPelleg D and Moore A 2000 Proceedings of the Seventeenth International Conference on Machine learning (ICML) (Stanford, USA: Stanford University) X-means: Extending K-means with efficient estimation of the number of clusters 727-734spa
dcterms.referencesEster M, Kriegel H, Sander J and Xu X 1996 Proceedings of the Second International Conference on Knowledge Discovery and Data Mining ed Evangelos Simoudis, Jiawei Han and Usama Fayyad (Portland, USA: AAAI American Association for Artificial Intelligence) A density-based algorithm for discovering clusters in large spatial databases with noise 226-231spa
dc.identifier.doihttps://doi.org/10.1088/1742-6596/1126/1/012035
dc.publisher.placeReino Unidospa
dc.relation.citationeditionVol.1126 No.1.(2018)spa
dc.relation.citationendpage8spa
dc.relation.citationissue1(2018)spa
dc.relation.citationstartpage1spa
dc.relation.citationvolume1126spa
dc.relation.citesPuerto, E., Aguilar, J., Reyes, J., & Sarkar, D. (2018, November). Deep learning architecture for the recursive patterns recognition model. In Journal of Physics: Conference Series (Vol. 1126, No. 1, p. 012035). IOP Publishing.
dc.relation.ispartofjournalJournal of Physics: Conference Seriesspa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.creativecommonsAtribución 4.0 Internacional (CC BY 4.0)spa
dc.type.coarhttp://purl.org/coar/resource_type/c_6501spa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/articlespa
dc.type.redcolhttp://purl.org/redcol/resource_type/ARTspa
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2spa
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85spa
dc.type.versioninfo:eu-repo/semantics/publishedVersionspa


Ficheros en el ítem

Thumbnail

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem