{"id":1137,"date":"2024-04-05T09:00:00","date_gmt":"2024-04-05T07:00:00","guid":{"rendered":"https:\/\/smalltalks.eu\/blog\/?p=1137"},"modified":"2026-10-06T11:24:03","modified_gmt":"2026-10-06T09:24:03","slug":"lalgorithme-le-plus-important-de-lapprentissage-automatique-artem-kirsanov","status":"publish","type":"post","link":"https:\/\/smalltalks.eu\/blog\/2024\/04\/05\/lalgorithme-le-plus-important-de-lapprentissage-automatique-artem-kirsanov\/","title":{"rendered":"L&#8217;algorithme le plus important de l&#8217;apprentissage automatique (Artem Kirsanov)"},"content":{"rendered":"\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"The Most Important Algorithm in Machine Learning\" width=\"640\" height=\"360\" src=\"https:\/\/www.youtube.com\/embed\/SmZmBKc7Lrs?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<div style=\"height:30px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p class=\"wp-block-paragraph\">Artem Kirsanov, doctorant en neurosciences \u00e0 Harvard, explique la r\u00e9tropropagation du gradient, l&#8217;algorithme qui fait tourner tout l&#8217;apprentissage automatique, et la red\u00e9montre \u00e0 partir des premiers principes.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Au programme : un peu d&#8217;histoire, le probl\u00e8me de l&#8217;ajustement de courbe, ajustements al\u00e9atoires ou guid\u00e9s, les d\u00e9riv\u00e9es, la descente de gradient, les dimensions sup\u00e9rieures, l&#8217;intuition de la r\u00e8gle de d\u00e9rivation en cha\u00eene, le graphe de calcul et la diff\u00e9rentiation automatique (en anglais).<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Voir aussi : <a href=\"https:\/\/smalltalks.eu\/blog\/?p=1139\">regarder un r\u00e9seau de neurones apprendre<\/a>, <a href=\"https:\/\/smalltalks.eu\/blog\/?p=1138\">ce que les r\u00e9seaux de neurones apprennent vraiment<\/a>.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><em>Vid\u00e9o d&#8217;Artem Kirsanov.<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Artem Kirsanov, doctorant en neurosciences \u00e0 Harvard, explique la r\u00e9tropropagation du gradient, l&#8217;algorithme qui fait tourner tout l&#8217;apprentissage automatique, et la red\u00e9montre \u00e0 partir des premiers principes. Au programme : un peu d&#8217;histoire, le probl\u00e8me de l&#8217;ajustement de courbe, ajustements al\u00e9atoires ou guid\u00e9s, les d\u00e9riv\u00e9es, la descente de gradient, les dimensions sup\u00e9rieures, l&#8217;intuition de la r\u00e8gle de d\u00e9rivation en cha\u00eene, le graphe de calcul et la diff\u00e9rentiation automatique (en anglais). Voir aussi : regarder un r\u00e9seau de neurones apprendre, ce&#8230;<\/p>\n<p class=\"read-more\"><a class=\"btn btn-default\" href=\"https:\/\/smalltalks.eu\/blog\/2024\/04\/05\/lalgorithme-le-plus-important-de-lapprentissage-automatique-artem-kirsanov\/\"> Read More<span class=\"screen-reader-text\">  Read More<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[282,110],"tags":[],"class_list":["post-1137","post","type-post","status-publish","format-standard","hentry","category-sciences-mathematiques","category-theme-intelligence-artificielle"],"_links":{"self":[{"href":"https:\/\/smalltalks.eu\/blog\/wp-json\/wp\/v2\/posts\/1137","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/smalltalks.eu\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/smalltalks.eu\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/smalltalks.eu\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/smalltalks.eu\/blog\/wp-json\/wp\/v2\/comments?post=1137"}],"version-history":[{"count":1,"href":"https:\/\/smalltalks.eu\/blog\/wp-json\/wp\/v2\/posts\/1137\/revisions"}],"predecessor-version":[{"id":1160,"href":"https:\/\/smalltalks.eu\/blog\/wp-json\/wp\/v2\/posts\/1137\/revisions\/1160"}],"wp:attachment":[{"href":"https:\/\/smalltalks.eu\/blog\/wp-json\/wp\/v2\/media?parent=1137"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/smalltalks.eu\/blog\/wp-json\/wp\/v2\/categories?post=1137"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/smalltalks.eu\/blog\/wp-json\/wp\/v2\/tags?post=1137"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}