{"id":58465,"date":"2018-03-09T22:46:20","date_gmt":"2018-03-09T22:46:20","guid":{"rendered":"https:\/\/www.deberes.net\/tesis\/sin-categoria\/redes-art-com-categorias-internas-de-geometria-irregular\/"},"modified":"2018-03-09T22:46:20","modified_gmt":"2018-03-09T22:46:20","slug":"redes-art-com-categorias-internas-de-geometria-irregular","status":"publish","type":"post","link":"https:\/\/www.deberes.net\/tesis\/santiago-de-compostela\/redes-art-com-categorias-internas-de-geometria-irregular\/","title":{"rendered":"Redes art com categorias internas de geometria irregular"},"content":{"rendered":"<h2>Tesis doctoral de <strong> Dinani Gomes Amorim <\/strong><\/h2>\n<p>En esta tesis se proponen varios modelos de redes neuronales art (adaptive resonance theory) que exploran las posibilidades de usar categor\u00edas internas con geometr\u00edas irregulares en problemas de clasificaci\u00f3n supervisada de patrones. Las redes art tradicionales usan categor\u00edas internas con geometr\u00edas pre-definidas (hiper-rect\u00e1ngulos o hiperelipsoides, b\u00e1sicamente) que tienen una capacidad limitada para aproximar las fronteras entre clases en problemas de clasificaci\u00f3n. El objetivo de esta tesis es el de dotar a estas redes de categor\u00edas internas con geometr\u00edas gen\u00e9ricas, de modo que la propia forma geom\u00e9trica de la categor\u00eda se aprenda durante la etapa de entrenamento supervisado, adapt\u00e1ndose a las caracter\u00edsticas geom\u00e9tricas del conjunto de entrenamiento.  el primer modelo propuesto ha sido simplex artmap, que usa categor\u00edas internas con forma geom\u00e9trica de s\u00edmplexes y funciones de activaci\u00f3n basadas en funciones gaussianas que toman valores no nulos s\u00f3lo en el interior del volumen del s\u00edmplex.  la segunda aproximaci\u00f3n propuesta, polytope artmap (ptam), est\u00e1 basado en categor\u00edas politopo&#8211; pol\u00edgono n-dimensional&#8211;, con funciones de activaci\u00f3n basadas en hiperplanos que delimitan las fronteras del politopo. En este modelo, el aprendizaje se realiza mediante la expansi\u00f3n de las categor\u00edas internas s\u00f3lo en la direcci\u00f3n del patr\u00f3n de entrada, sin necesidad de superponerse entre ellas. De este modo, las propias categor\u00edas limitan su expansi\u00f3n entre ellas, sin necesidad de ning\u00fan tama\u00f1o m\u00e1ximo ni par\u00e1metro de vigilancia. Esto permite que  ptam opere de modo completamente autom\u00e1tico, sin ning\u00fan par\u00e1metro optimizable. Ptam se ha validado sobre varios problemas est\u00e1ndar de clasificaci\u00f3n, mostrando una mayor capacidad de aprendizaje y adaptaci\u00f3n a distintas geometr\u00edas que las redes art cl\u00e1sicas, sin necesidad de sintonizar la vigilancia. Tambi\u00e9n se ha experimentado usando categor\u00edas internas con geometr\u00eda politopo permitiend<\/p>\n<p>&nbsp;<\/p>\n<h3>Datos acad\u00e9micos de la tesis doctoral \u00ab<strong>Redes art com categorias internas de geometria irregular<\/strong>\u00ab<\/h3>\n<ul>\n<li><strong>T\u00edtulo de la tesis:<\/strong>\u00a0 Redes art com categorias internas de geometria irregular <\/li>\n<li><strong>Autor:<\/strong>\u00a0 Dinani Gomes Amorim <\/li>\n<li><strong>Universidad:<\/strong>\u00a0 Santiago de compostela<\/li>\n<li><strong>Fecha de lectura de la tesis:<\/strong>\u00a0 15\/05\/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>Manuel Fernandez Delgado<\/li>\n<\/ul>\n<\/li>\n<li><strong>Tribunal<\/strong>\n<ul>\n<li>Presidente del tribunal: diego Cabello ferrer <\/li>\n<li>ram\u00f3n Ruiz merino (vocal)<\/li>\n<li> Ferreira maia neves Jos\u00e9 Carlos (vocal)<\/li>\n<li> Francelin romero roseli aparecida (vocal)<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Tesis doctoral de Dinani Gomes Amorim En esta tesis se proponen varios modelos de redes neuronales art (adaptive resonance theory) [&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":[2528,7953,977],"tags":[21468,129200,120723,129201,101428,2532],"class_list":["post-58465","post","type-post","status-publish","format-standard","hentry","category-inteligencia-artificial","category-redes-neuronales","category-santiago-de-compostela","tag-diego-cabello-ferrer","tag-dinani-gomes-amorim","tag-ferreira-maia-neves-jose-carlos","tag-francelin-romero-roseli-aparecida","tag-manuel-fernandez-delgado","tag-ramon-ruiz-merino"],"_links":{"self":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/58465","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=58465"}],"version-history":[{"count":0,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/58465\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/media?parent=58465"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/categories?post=58465"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/tags?post=58465"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}