{"id":18829,"date":"2002-06-09T00:00:00","date_gmt":"2002-06-09T00:00:00","guid":{"rendered":"https:\/\/www.deberes.net\/tesis\/sin-categoria\/modelos-predictivos-basados-en-redes-neuronales-recurrentes-de-tiempo-discreto\/"},"modified":"2002-06-09T00:00:00","modified_gmt":"2002-06-09T00:00:00","slug":"modelos-predictivos-basados-en-redes-neuronales-recurrentes-de-tiempo-discreto","status":"publish","type":"post","link":"https:\/\/www.deberes.net\/tesis\/linguistica\/modelos-predictivos-basados-en-redes-neuronales-recurrentes-de-tiempo-discreto\/","title":{"rendered":"Modelos predictivos basados en redes neuronales recurrentes de tiempo discreto"},"content":{"rendered":"<h2>Tesis doctoral de <strong> Juan  Antonio P\u00e9rez Ortiz <\/strong><\/h2>\n<p>Este trabajo estudia la aplicaci\u00f3n de distintos modelos de redes neuronales recurrentes de tiempo discreto a diversas tareas de car\u00e1cter predictivo.  las redes neuronales recurrentes son redes neuronales que presentan uno o m\u00e1s ciclos en el grafo definido por las interconexiones de sus unidades de procesamiento. La existencia de estos ciclos les permite trabajar de forma innata con secuencias temporales. Las redes recurrentes son sistemas din\u00e1micos no lineales capaces de descubrir regularidades temporales en las secuencias procesadas y pueden aplicarse, por lo tanto, a multitud de tareas de procesamiento de este tipo de secuencias. Esta tesis se centra en la aplicaci\u00f3n de las redes neuronales recurrentes a la predicci\u00f3n del siguiente elemento de secuencias de naturaleza simb\u00f3lica o num\u00e9rica.  no obstante, la predicci\u00f3n en s\u00ed no es el objetivo \u00faltimo: en esta tesis la capacidad predictiva de las redes recurrentes se aplica a la comprensi\u00f3n de se\u00f1ales de voz o de secuencias de texto, a la inferencia de lenguajes regulares o sensibles al contexto, y a la desambiguaci\u00f3n de las palabras hom\u00f3grafas de una oraci\u00f3n.  los modelos concretos de redes utilizados son, principalmente, la red recurrente simple, la red parcialmente recurrente y el modelo neuronal de memoria a corto y largo plazo; este \u00faltimo permite superar el llamado problema del gradiente evanescente que aparece cuando los intervalos de tiempo m\u00ednimos entre eventos interdependientes son relativamente largos. para determinar valores correctos de los par\u00e1metros libres de las redes se usan dos algoritmos, el cl\u00e1sico algoritmo del descenso por el gradiente y una forma del filtro de kalman extendido.<\/p>\n<p>&nbsp;<\/p>\n<h3>Datos acad\u00e9micos de la tesis doctoral \u00ab<strong>Modelos predictivos basados en redes neuronales recurrentes de tiempo discreto<\/strong>\u00ab<\/h3>\n<ul>\n<li><strong>T\u00edtulo de la tesis:<\/strong>\u00a0 Modelos predictivos basados en redes neuronales recurrentes de tiempo discreto <\/li>\n<li><strong>Autor:<\/strong>\u00a0 Juan  Antonio P\u00e9rez Ortiz <\/li>\n<li><strong>Universidad:<\/strong>\u00a0 Alicante<\/li>\n<li><strong>Fecha de lectura de la tesis:<\/strong>\u00a0 06\/09\/2002<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h3>Direcci\u00f3n y tribunal<\/h3>\n<ul>\n<li><strong>Director de la tesis<\/strong>\n<ul>\n<li>Mikel Lorenzo Forcada Zubizarreta<\/li>\n<\/ul>\n<\/li>\n<li><strong>Tribunal<\/strong>\n<ul>\n<li>Presidente del tribunal: rafael Carrasco jim\u00e9nez <\/li>\n<li> Castro bleda Mar\u00eda  Jos\u00e9 (vocal)<\/li>\n<li>renato Alqu\u00e9zar mancho (vocal)<\/li>\n<li> De la higuera colin (vocal)<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Tesis doctoral de Juan Antonio P\u00e9rez Ortiz Este trabajo estudia la aplicaci\u00f3n de distintos modelos de redes neuronales recurrentes de [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""}},"footnotes":""},"categories":[19166,1890,2528,59,60,3747,3748,126,30772,656],"tags":[53405,38865,58184,53901,58185,58186],"class_list":["post-18829","post","type-post","status-publish","format-standard","hentry","category-alicante","category-ciencia-de-los-ordenadores","category-inteligencia-artificial","category-linguistica","category-linguistica-aplicada","category-logica","category-logica-deductiva","category-matematicas","category-teoria-de-lenguajes-formales","category-traduccion-automatica","tag-castro-bleda-maria-jose","tag-de-la-higuera-colin","tag-juan-antonio-perez-ortiz","tag-mikel-lorenzo-forcada-zubizarreta","tag-rafael-carrasco-jimenez","tag-renato-alquezar-mancho"],"_links":{"self":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/18829","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/comments?post=18829"}],"version-history":[{"count":0,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/18829\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/media?parent=18829"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/categories?post=18829"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/tags?post=18829"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}