En apprentissage automatique et en prompt engineering, l’underfitting est un ph\u00e9nom\u00e8ne courant qui peut limiter les performances de vos mod\u00e8les. Qu’est-ce que l’underfitting ? C’est lorsque votre mod\u00e8le est trop simple pour capturer la complexit\u00e9 des donn\u00e9es d’entra\u00eenement, ce qui entra\u00eene de mauvaises performances \u00e0 la fois sur les donn\u00e9es d’entra\u00eenement et sur les donn\u00e9es de test.<\/p>\n
Imaginez que vous essayez d’apprendre \u00e0 un enfant \u00e0 reconna\u00eetre des formes g\u00e9om\u00e9triques uniquement en lui montrant des carr\u00e9s. L’enfant pourrait conclure que toutes les formes \u00e0 quatre c\u00f4t\u00e9s sont des carr\u00e9s. Lorsqu’il rencontrera un rectangle ou un losange, il le classera incorrectement comme un carr\u00e9. De la m\u00eame mani\u00e8re, un mod\u00e8le en underfitting est trop simpliste et ne parvient pas \u00e0 g\u00e9n\u00e9raliser correctement \u00e0 de nouvelles donn\u00e9es. Il a appris les donn\u00e9es d’entra\u00eenement de mani\u00e8re trop superficielle. En prompt engineering, cela se traduit par des prompts trop g\u00e9n\u00e9riques qui ne guident pas le mod\u00e8le vers la r\u00e9ponse souhait\u00e9e.<\/p>\n
L’underfitting est un probl\u00e8me car il signifie que votre mod\u00e8le n’apprend pas efficacement \u00e0 partir des donn\u00e9es. En cons\u00e9quence, les pr\u00e9dictions du mod\u00e8le seront impr\u00e9cises, m\u00eame sur les donn\u00e9es qu’il a d\u00e9j\u00e0 vues. En prompt engineering, un mod\u00e8le en underfitting peut g\u00e9n\u00e9rer des r\u00e9ponses hors sujet ou trop g\u00e9n\u00e9rales, ne r\u00e9pondant pas \u00e0 la sp\u00e9cificit\u00e9 de votre requ\u00eate. Par exemple, si vous demandez \u00e0 un mod\u00e8le de g\u00e9n\u00e9rer une histoire sur un chat et un chien qui deviennent amis et que le prompt est trop vague, le mod\u00e8le peut g\u00e9n\u00e9rer une histoire g\u00e9n\u00e9rique sur l’amiti\u00e9 sans int\u00e9grer les \u00e9l\u00e9ments sp\u00e9cifiques du chat et du chien.<\/p>\n
En apprentissage automatique et en prompt engineering, l’underfitting est un ph\u00e9nom\u00e8ne courant qui peut limiter les performances de vos mod\u00e8les. Qu’est-ce que l’underfitting ? C’est lorsque votre mod\u00e8le est trop simple pour capturer la complexit\u00e9 des donn\u00e9es d’entra\u00eenement, ce qui entra\u00eene de mauvaises performances \u00e0 la fois sur les donn\u00e9es d’entra\u00eenement et sur les donn\u00e9es […]<\/p>\n","protected":false},"author":0,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_uag_custom_page_level_css":"","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-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":"","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-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":"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":""},"mobile":{"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":""}},"footnotes":""},"categories":[404],"tags":[153,584,583,585],"class_list":["post-1145","post","type-post","status-publish","format-standard","hentry","category-u","tag-biais","tag-overfitting","tag-underfitting","tag-variance"],"uagb_featured_image_src":{"full":false,"thumbnail":false,"medium":false,"medium_large":false,"large":false,"1536x1536":false,"2048x2048":false},"uagb_author_info":{"display_name":"","author_link":"https:\/\/happynumeric.com\/lexique-intelligence-artificielle\/author\/"},"uagb_comment_info":0,"uagb_excerpt":"En apprentissage automatique et en prompt engineering, l’underfitting est un ph\u00e9nom\u00e8ne courant qui peut limiter les performances de vos mod\u00e8les. Qu’est-ce que l’underfitting ? C’est lorsque votre mod\u00e8le est trop simple pour capturer la complexit\u00e9 des donn\u00e9es d’entra\u00eenement, ce qui entra\u00eene de mauvaises performances \u00e0 la fois sur les donn\u00e9es d’entra\u00eenement et sur les donn\u00e9es\u2026","_links":{"self":[{"href":"https:\/\/happynumeric.com\/lexique-intelligence-artificielle\/wp-json\/wp\/v2\/posts\/1145","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/happynumeric.com\/lexique-intelligence-artificielle\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/happynumeric.com\/lexique-intelligence-artificielle\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/happynumeric.com\/lexique-intelligence-artificielle\/wp-json\/wp\/v2\/comments?post=1145"}],"version-history":[{"count":0,"href":"https:\/\/happynumeric.com\/lexique-intelligence-artificielle\/wp-json\/wp\/v2\/posts\/1145\/revisions"}],"wp:attachment":[{"href":"https:\/\/happynumeric.com\/lexique-intelligence-artificielle\/wp-json\/wp\/v2\/media?parent=1145"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/happynumeric.com\/lexique-intelligence-artificielle\/wp-json\/wp\/v2\/categories?post=1145"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/happynumeric.com\/lexique-intelligence-artificielle\/wp-json\/wp\/v2\/tags?post=1145"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}