{"id":3151,"date":"2022-04-27T10:22:06","date_gmt":"2022-04-27T15:22:06","guid":{"rendered":"https:\/\/academia.utp.edu.co\/sneia\/?p=3151"},"modified":"2024-02-08T21:13:51","modified_gmt":"2024-02-09T02:13:51","slug":"regularizacion-en-una-red-neuronal","status":"publish","type":"post","link":"https:\/\/academia.utp.edu.co\/sneia\/regularizacion-en-una-red-neuronal\/","title":{"rendered":"Regularizaci\u00f3n en una Red Neuronal"},"content":{"rendered":"<figure class=\"wp-block-post-featured-image\"><img loading=\"lazy\" decoding=\"async\" width=\"1920\" height=\"1004\" src=\"https:\/\/academia.utp.edu.co\/sneia\/files\/2022\/04\/artificialIntelligenceConceptualImage.jpg\" class=\"attachment-post-thumbnail size-post-thumbnail wp-post-image\" alt=\"Imagen conceptual de inteligencia artificial.\" style=\"object-fit:cover;\" srcset=\"https:\/\/academia.utp.edu.co\/sneia\/files\/2022\/04\/artificialIntelligenceConceptualImage.jpg 1920w, https:\/\/academia.utp.edu.co\/sneia\/files\/2022\/04\/artificialIntelligenceConceptualImage-300x157.jpg 300w, https:\/\/academia.utp.edu.co\/sneia\/files\/2022\/04\/artificialIntelligenceConceptualImage-1024x535.jpg 1024w, https:\/\/academia.utp.edu.co\/sneia\/files\/2022\/04\/artificialIntelligenceConceptualImage-768x402.jpg 768w, https:\/\/academia.utp.edu.co\/sneia\/files\/2022\/04\/artificialIntelligenceConceptualImage-1536x803.jpg 1536w\" sizes=\"auto, (max-width: 1920px) 100vw, 1920px\" \/><\/figure>\n\n\n<div style=\"height:50px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p>Probablemente el concepto de <em><strong>overfitting<\/strong><\/em> sea conocido para algunos, y en ciertas ocasiones podr\u00eda llegar a ser poco productivo para nuestros <em>modelos de redes neuronales<\/em>; Entonces, aqu\u00ed entra el tema que se tocar\u00e1 en este art\u00edculo, la <strong><em>regularizaci\u00f3n de redes neuronales<\/em><\/strong>.<\/p>\n\n\n\n<p>La <strong><em>regularizaci\u00f3n<\/em><\/strong> en una <em>red neuronal<\/em> es una t\u00e9cnica que podemos  utilizar para <em><strong>reducir el overfitting<\/strong><\/em> en nuestro <em>modelo de red neuronal<\/em> y, eventualmente, <strong>optimizar<\/strong> este mismo.<\/p>\n\n\n\n<p>Definitivamente es un concepto muy amplio, \u00fatil y relativamente extenso, pero no est\u00e1 mal conocer un poco de este. Hay varias <strong><em>t\u00e9cnicas de regularizaci\u00f3n<\/em><\/strong> que podemos usar, por ejemplo, est\u00e1 la <strong><em>t\u00e9cnica L2 de regularizaci\u00f3n de redes neuronales<\/em><\/strong>, la cu\u00e1l consta (A pocas palabras) de <strong>reducir el valor de los par\u00e1metros del modelo para que sean peque\u00f1os<\/strong>. Entre muchos otros est\u00e1n las t\u00e9cnicas de, por ejemplo: <strong><em>Regularizaci\u00f3n L1<\/em><\/strong>, <strong><em>Weight Decay<\/em><\/strong>, <strong><em>Dropout<\/em><\/strong>, <strong><em>Batch Normalization<\/em><\/strong>, entre otros.<\/p>\n\n\n\n<div style=\"height:50px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<div class=\"wp-block-buttons is-content-justification-center is-layout-flex wp-container-core-buttons-is-layout-a89b3969 wp-block-buttons-is-layout-flex\">\n<div class=\"wp-block-button is-style-outline is-style-outline--1\"><a class=\"wp-block-button__link\" href=\"https:\/\/deeplizard.com\/learn\/video\/iuJgyiS7BKM\" target=\"_blank\" rel=\"noreferrer noopener\">Leer m\u00e1s al respecto<\/a><\/div>\n<\/div>\n\n\n\n<div style=\"height:100px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n","protected":false},"excerpt":{"rendered":"<p>\u00bfQu\u00e9 es la regularizaci\u00f3n de redes neuronales? \u00bfEst\u00e1 relacionado con el overfitting?<\/p>\n","protected":false},"author":1571,"featured_media":3161,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_uag_custom_page_level_css":"","site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","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":"","ast-disable-related-posts":"","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-opacity":"","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-opacity":"","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-opacity":"","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-opacity":"","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-opacity":"","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-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[271],"tags":[411,421,221,431,441],"class_list":["post-3151","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-recursos","tag-deep-learning","tag-inteligencia-artificial","tag-machine-learning","tag-overfitting","tag-regularizacion-de-redes-neuronales"],"uagb_featured_image_src":{"full":["https:\/\/academia.utp.edu.co\/sneia\/files\/2022\/04\/artificialIntelligenceConceptualImage.jpg",1920,1004,false],"thumbnail":["https:\/\/academia.utp.edu.co\/sneia\/files\/2022\/04\/artificialIntelligenceConceptualImage-150x150.jpg",150,150,true],"medium":["https:\/\/academia.utp.edu.co\/sneia\/files\/2022\/04\/artificialIntelligenceConceptualImage-300x157.jpg",300,157,true],"medium_large":["https:\/\/academia.utp.edu.co\/sneia\/files\/2022\/04\/artificialIntelligenceConceptualImage-768x402.jpg",768,402,true],"large":["https:\/\/academia.utp.edu.co\/sneia\/files\/2022\/04\/artificialIntelligenceConceptualImage-1024x535.jpg",1024,535,true],"1536x1536":["https:\/\/academia.utp.edu.co\/sneia\/files\/2022\/04\/artificialIntelligenceConceptualImage-1536x803.jpg",1536,803,true],"2048x2048":["https:\/\/academia.utp.edu.co\/sneia\/files\/2022\/04\/artificialIntelligenceConceptualImage.jpg",1920,1004,false]},"uagb_author_info":{"display_name":"jrivera","author_link":"https:\/\/academia.utp.edu.co\/sneia\/author\/jrivera\/"},"uagb_comment_info":0,"uagb_excerpt":"\u00bfQu\u00e9 es la regularizaci\u00f3n de redes neuronales? \u00bfEst\u00e1 relacionado con el overfitting?","_links":{"self":[{"href":"https:\/\/academia.utp.edu.co\/sneia\/wp-json\/wp\/v2\/posts\/3151","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/academia.utp.edu.co\/sneia\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/academia.utp.edu.co\/sneia\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/academia.utp.edu.co\/sneia\/wp-json\/wp\/v2\/users\/1571"}],"replies":[{"embeddable":true,"href":"https:\/\/academia.utp.edu.co\/sneia\/wp-json\/wp\/v2\/comments?post=3151"}],"version-history":[{"count":3,"href":"https:\/\/academia.utp.edu.co\/sneia\/wp-json\/wp\/v2\/posts\/3151\/revisions"}],"predecessor-version":[{"id":3191,"href":"https:\/\/academia.utp.edu.co\/sneia\/wp-json\/wp\/v2\/posts\/3151\/revisions\/3191"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/academia.utp.edu.co\/sneia\/wp-json\/wp\/v2\/media\/3161"}],"wp:attachment":[{"href":"https:\/\/academia.utp.edu.co\/sneia\/wp-json\/wp\/v2\/media?parent=3151"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/academia.utp.edu.co\/sneia\/wp-json\/wp\/v2\/categories?post=3151"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/academia.utp.edu.co\/sneia\/wp-json\/wp\/v2\/tags?post=3151"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}