{"id":59818,"date":"2007-10-07T00:00:00","date_gmt":"2007-10-07T00:00:00","guid":{"rendered":"https:\/\/www.deberes.net\/tesis\/sin-categoria\/enfriamiento-funcional-para-optimizacion-fundamentos-teoricos-y-aplicacion-a-las-redes-neuronales\/"},"modified":"2007-10-07T00:00:00","modified_gmt":"2007-10-07T00:00:00","slug":"enfriamiento-funcional-para-optimizacion-fundamentos-teoricos-y-aplicacion-a-las-redes-neuronales","status":"publish","type":"post","link":"https:\/\/www.deberes.net\/tesis\/inteligencia-artificial\/enfriamiento-funcional-para-optimizacion-fundamentos-teoricos-y-aplicacion-a-las-redes-neuronales\/","title":{"rendered":"Enfriamiento funcional para optimizaci\u00f3n. fundamentos te\u00f3ricos y aplicaci\u00f3n a las redes neuronales"},"content":{"rendered":"<h2>Tesis doctoral de <strong> Domingo L\u00f3pez Rodr\u00edguez <\/strong><\/h2>\n<p>El objetivo de este trabajo es describir un modelo matem\u00e1tico de optimizaci\u00f3n global, que nos permitir\u00e1 escapar de ciertos m\u00ednimos locales de la funci\u00f3n objetivo.     este modelo matem\u00e1tico se basa en la idea de aproximar dicha funci\u00f3n objetivo, mediante una sucesi\u00f3n de funciones que converja hacia ella. A cada una de esas funciones aproximadoras se le aplicar\u00e1 un algoritmo de optimizaci\u00f3n, para calcular uno de sus m\u00ednimos. El punto inicial para minimizar una funci\u00f3n aproximadora es el m\u00ednimo local (o una aproximaci\u00f3n suya) de la funci\u00f3n aproximadora anterior. De esta forma, los m\u00ednimos respectivos de dichas funciones coverger\u00e1n, bajo condiciones bastante generales, hacia un m\u00ednimo de la funci\u00f3n objetivo original. a lo largo de este trabajo estudiaremos las distintas situaciones, o casos, en los que esta formulaci\u00f3n resulta aplicable. concretamente, el modelo se ha desarrollado tanto para optimizaci\u00f3n en espacios continuos, como para espacios finitos (que generalmente se corresponden con problemas de optimizaci\u00f3n combinatoria). Adem\u00e1s, se han formalizado las versiones tanto determinista (en la que en cada \u00abfase\u00bb del modelo se asegura la minimizaci\u00f3n de una funci\u00f3n objetivo), como estoc\u00e1stica (cuando la optimizaci\u00f3n de la funci\u00f3n objetivo s\u00f3lo se consigue en el l\u00edmite). asimismo, el modelo se ha aplicado a las redes neuronales, particularmente a las redes competitivas  y a las recurrentes.<\/p>\n<p>&nbsp;<\/p>\n<h3>Datos acad\u00e9micos de la tesis doctoral \u00ab<strong>Enfriamiento funcional para optimizaci\u00f3n. fundamentos te\u00f3ricos y aplicaci\u00f3n a las redes neuronales<\/strong>\u00ab<\/h3>\n<ul>\n<li><strong>T\u00edtulo de la tesis:<\/strong>\u00a0 Enfriamiento funcional para optimizaci\u00f3n. fundamentos te\u00f3ricos y aplicaci\u00f3n a las redes neuronales <\/li>\n<li><strong>Autor:<\/strong>\u00a0 Domingo L\u00f3pez Rodr\u00edguez <\/li>\n<li><strong>Universidad:<\/strong>\u00a0 M\u00e1laga<\/li>\n<li><strong>Fecha de lectura de la tesis:<\/strong>\u00a0 10\/07\/2007<\/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>Enrique Merida Casermeiro<\/li>\n<\/ul>\n<\/li>\n<li><strong>Tribunal<\/strong>\n<ul>\n<li>Presidente del tribunal: inmaculada Perez de guzman molina <\/li>\n<li>c\u00e9sar Herv\u00e1s mart\u00ednez (vocal)<\/li>\n<li>Jos\u00e9 Mu\u00f1oz p\u00e9rez (vocal)<\/li>\n<li>ignacio Requena ramos (vocal)<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Tesis doctoral de Domingo L\u00f3pez Rodr\u00edguez El objetivo de este trabajo es describir un modelo matem\u00e1tico de optimizaci\u00f3n global, que [&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":[16880,37303,2528,7834],"tags":[20815,132124,76654,53597,24725,24726],"class_list":["post-59818","post","type-post","status-publish","format-standard","hentry","category-construccion-de-algoritmos","category-heuristica","category-inteligencia-artificial","category-malaga","tag-cesar-hervas-Martinez","tag-domingo-lopez-rodriguez","tag-enrique-merida-casermeiro","tag-ignacio-requena-ramos","tag-inmaculada-perez-de-guzman-molina","tag-jose-munoz-perez"],"_links":{"self":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/59818","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=59818"}],"version-history":[{"count":0,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/59818\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/media?parent=59818"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/categories?post=59818"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/tags?post=59818"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}