{"id":2444,"date":"2019-10-23T12:42:59","date_gmt":"2019-10-23T12:42:59","guid":{"rendered":"http:\/\/skimai.com\/?p=2444"},"modified":"2024-05-20T07:38:38","modified_gmt":"2024-05-20T12:38:38","slug":"algorithmes-de-recommandation-neuronale","status":"publish","type":"post","link":"https:\/\/skimai.com\/fr\/neural-recommendation-algorithms\/","title":{"rendered":"Les approches de recommandation neuronale progressent-elles vraiment ?"},"content":{"rendered":"<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_82_1 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Table des mati\u00e8res<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table des mati\u00e8res\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewbox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewbox=\"0 0 24 24\" version=\"1.2\" baseprofile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1' ><li class='ez-toc-page-1 ez-toc-heading-level-1'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/skimai.com\/fr\/neural-recommendation-algorithms\/#Are_We_Really_Making_Progress_on_Neural_Recommendation_Approaches\" >Avan\u00e7ons-nous vraiment sur les approches de recommandation neuronale ?\nneuronales ?<\/a><ul class='ez-toc-list-level-4' ><li class='ez-toc-heading-level-4'><ul class='ez-toc-list-level-4' ><li class='ez-toc-heading-level-4'><ul class='ez-toc-list-level-4' ><li class='ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/skimai.com\/fr\/neural-recommendation-algorithms\/#A_summary_of_Maurizio_Ferrari_Dacrema_et_als_Recent_Article_at_RecSys_2019%E2%80%8B\" >R\u00e9sum\u00e9 de l'article r\u00e9cent de Maurizio Ferrari Dacrema, et al. \u00e0 RecSys 2019<\/a><\/li><\/ul><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/skimai.com\/fr\/neural-recommendation-algorithms\/#Neural_Recommendation_Algorithms\" >Algorithmes de recommandation neuronale<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/skimai.com\/fr\/neural-recommendation-algorithms\/#How_Progress_is_Measured\" >Comment les progr\u00e8s sont-ils mesur\u00e9s ?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/skimai.com\/fr\/neural-recommendation-algorithms\/#Why_Are_These_Methods_Failing\" >Pourquoi ces m\u00e9thodes \u00e9chouent-elles ?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/skimai.com\/fr\/neural-recommendation-algorithms\/#Neural_Recommendation_Have_We_Improved\" >Recommandation neuronale : Avons-nous progress\u00e9 ?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/skimai.com\/fr\/neural-recommendation-algorithms\/#Summary\" >R\u00e9sum\u00e9<\/a><\/li><\/ul><\/li><\/ul><\/nav><\/div>\n<h1><span class=\"ez-toc-section\" id=\"Are_We_Really_Making_Progress_on_Neural_Recommendation_Approaches\"><\/span>Avan\u00e7ons-nous vraiment dans le domaine des neurones ?<br \/>\nApproches de recommandation ?<span class=\"ez-toc-section-end\"><\/span><\/h1>\n<pre><code>        <h4><span class=\"ez-toc-section\" id=\"A_summary_of_Maurizio_Ferrari_Dacrema_et_als_Recent_Article_at_RecSys_2019%E2%80%8B\"><\/span>R\u00e9sum\u00e9 de l'article r\u00e9cent de Maurizio Ferrari Dacrema, et al. \u00e0 RecSys 2019<span class=\"ez-toc-section-end\"><\/span><\/h4>     \n    <h2><span class=\"ez-toc-section\" id=\"Neural_Recommendation_Algorithms\"><\/span><strong>Algorithmes de recommandation neuronale<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2>Les algorithmes de recommandation sont devenus omnipr\u00e9sents dans les domaines commerciaux, de la page d'accueil \"yourstore\" d'Amazon aux scores % de Netflix. Les algorithmes de recommandation filtrent essentiellement de grands ensembles de donn\u00e9es, par exemple des bases de donn\u00e9es de chansons ou de films, en utilisant une vari\u00e9t\u00e9 de m\u00e9thodes pour rep\u00e9rer les \u00e9l\u00e9ments les plus pertinents pour un utilisateur. Pour ce faire, l'algorithme examine le comportement ant\u00e9rieur de l'utilisateur et utilise les connaissances acquises \u00e0 partir de ces observations pour recommander les produits et les m\u00e9dias que l'utilisateur est le plus susceptible d'acheter, de regarder ou d'\u00e9couter. De nombreuses tentatives ont \u00e9t\u00e9 faites pour tirer parti de l'apprentissage automatique, en particulier des r\u00e9seaux neuronaux, pour les syst\u00e8mes de recommandation. Bien qu'il existe un grand nombre de recherches faisant \u00e9tat d'am\u00e9liorations dans les recommandations pour divers algorithmes, Dacrema et al. ont \u00e9crit un article \u00e9clairant dans lequel ils se demandent si nous am\u00e9liorons vraiment les techniques traditionnelles. Selon cet article, \"... il existe des indications... que les progr\u00e8s r\u00e9alis\u00e9s - mesur\u00e9s en termes d'am\u00e9lioration de la pr\u00e9cision par rapport aux mod\u00e8les existants - ne sont pas toujours aussi importants que pr\u00e9vu\". Alors, si les progr\u00e8s ne sont pas saisis avec pr\u00e9cision, comment les chercheurs mesurent-ils actuellement les progr\u00e8s, quels sont les d\u00e9fauts de ces m\u00e9thodes, et avons-nous r\u00e9ellement am\u00e9lior\u00e9 les algorithmes de recommandation en ajoutant des techniques d'apprentissage automatique ?<\/p><h2><span class=\"ez-toc-section\" id=\"How_Progress_is_Measured\"><\/span><strong>Comment les progr\u00e8s sont-ils mesur\u00e9s ?<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2><p>Les progr\u00e8s dans la performance des algorithmes sont mesur\u00e9s en comparant la performance d'un nouvel algorithme \u00e0 la performance de r\u00e9f\u00e9rence d'autres algorithmes \u00e9tendus. En particulier, les mesures les plus couramment utilis\u00e9es sont les suivantes :<\/p><ul><li>Pr\u00e9cision : La capacit\u00e9 d'un mod\u00e8le de classification \u00e0 identifier uniquement les points de donn\u00e9es pertinents.<\/li><li>Rappel : La capacit\u00e9 d'un mod\u00e8le \u00e0 trouver tous les points de donn\u00e9es pertinents dans un ensemble de donn\u00e9es.<\/li><li>Gain cumulatif actualis\u00e9 normalis\u00e9 (NDCG) : comparaison entre la liste de r\u00e9f\u00e9rence class\u00e9e (g\u00e9n\u00e9ralement jug\u00e9e par l'homme) et la liste class\u00e9e par l'algorithme.<\/li><\/ul><h2><span class=\"ez-toc-section\" id=\"Why_Are_These_Methods_Failing\"><\/span><strong>Pourquoi ces m\u00e9thodes \u00e9chouent-elles ?<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2><p>Si plusieurs facteurs contribuent \u00e0 l'\u00e9chec des m\u00e9thodes actuelles d'\u00e9valuation des progr\u00e8s, Decrema et al. en soulignent trois principaux :<\/p><ol><li>Des ensembles de donn\u00e9es de r\u00e9f\u00e9rence faibles pour la formation et l'\u00e9valuation<\/li><li>M\u00e9thodes faibles utilis\u00e9es pour les nouvelles lignes de base (utilisation d'algorithmes publi\u00e9s ant\u00e9rieurement mais non v\u00e9rifi\u00e9s pour la comparaison des performances)<\/li><li>Impossibilit\u00e9 de comparer et de <em>reproduire<\/em> les r\u00e9sultats obtenus dans les diff\u00e9rents documents<\/li><\/ol><p>Les auteurs soulignent notamment le manque extr\u00eame de reproductibilit\u00e9 des algorithmes publi\u00e9s. Ils s'empressent de souligner que dans l'environnement de recherche moderne, o\u00f9 le code source et les ensembles de donn\u00e9es sont facilement accessibles, les r\u00e9sultats publi\u00e9s devraient \u00eatre faciles \u00e0 recr\u00e9er. Cependant, \"en r\u00e9alit\u00e9, il y a ... de minuscules d\u00e9tails concernant la mise en \u0153uvre des algorithmes et la proc\u00e9dure d'\u00e9valuation ... qui peuvent avoir un impact sur les r\u00e9sultats de l'exp\u00e9rience\". En fait, sur les dizaines d'articles examin\u00e9s, les auteurs n'en ont trouv\u00e9 que sept avec un code source et des ensembles de donn\u00e9es pouvant \u00eatre reproduits.<\/p><h2><span class=\"ez-toc-section\" id=\"Neural_Recommendation_Have_We_Improved\"><\/span><strong>Recommandation neuronale : Avons-nous progress\u00e9 ?<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2><p>Dacrema et al. ont test\u00e9 sept algorithmes publi\u00e9s dans leur article. Ils ont compar\u00e9 les r\u00e9sultats de ces algorithmes, \u00e0 l'aide des donn\u00e9es utilis\u00e9es dans les \u00e9tudes respectives, aux r\u00e9sultats des algorithmes traditionnels, beaucoup plus simples. Dans leur \u00e9tude, ils n'ont trouv\u00e9 qu'un seul algorithme plus performant que les m\u00e9thodes traditionnelles : Variational Autoencoders for Collaborative Filtering (Mult-VAE), pr\u00e9sent\u00e9 par Liang et al. en 2018. Decrema et al. affirment que Mult-VAE apporte les am\u00e9liorations de performance suivantes :<\/p><ul><li>Les r\u00e9sultats obtenus sont entre 10% et 20% meilleurs que la m\u00e9thode lin\u00e9aire simple (SLIM) pr\u00e9sent\u00e9e par Xia Ning et George Karypis en 2011 \u00e0 l'IDCM 11, qui \u00e9tait la meilleure performance de l'algorithme de base.<\/li><li>Les r\u00e9sultats ont pu \u00eatre reproduits avec des am\u00e9liorations par rapport \u00e0 SLIM allant jusqu'\u00e0 5% pour toutes les mesures de performance.<\/li><li>Les am\u00e9liorations du rappel de Mult-VAE par rapport \u00e0 SLIM \"semblent solides\".<\/li><\/ul><p>Decrema et al. concluent en d\u00e9clarant : \"Ainsi, avec Mult-VAE, nous avons trouv\u00e9 un exemple dans la litt\u00e9rature examin\u00e9e o\u00f9 une m\u00e9thode plus complexe \u00e9tait meilleure ... que n'importe laquelle de nos techniques de base dans toutes les configurations\".<\/p><h2><span class=\"ez-toc-section\" id=\"Summary\"><\/span><strong>R\u00e9sum\u00e9<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2><p>M\u00eame s'il est tentant d'annoncer un succ\u00e8s et de publier de nouveaux algorithmes et r\u00e9sultats, l'\u00e9quipe de Dacrema a montr\u00e9 que nous ne nous am\u00e9liorons pas vraiment, ou du moins pas beaucoup. L'article conclut en d\u00e9clarant : \"Notre analyse indique que ... la plupart des travaux examin\u00e9s peuvent \u00eatre surpass\u00e9s, au moins sur certains ensembles de donn\u00e9es, par des algorithmes plus simples sur le plan conceptuel et informatique\". Par cons\u00e9quent, m\u00eame s'il est tentant d'appliquer l'apprentissage automatique \u00e0 toutes les applications d'analyse de donn\u00e9es, les syst\u00e8mes de recommandation se sont jusqu'\u00e0 pr\u00e9sent r\u00e9v\u00e9l\u00e9s \u00eatre une application pour laquelle l'apprentissage automatique n'a pas am\u00e9lior\u00e9 les performances des algorithmes ; du moins, pas encore.<\/code><\/pre>","protected":false},"excerpt":{"rendered":"<p>Are We Really Making Progress on Neural Recommendation Approaches? A summary of Maurizio Ferrari Dacrema, et al.\u2019s Recent Article at RecSys 2019\u200b Neural Recommendation AlgorithmsRecommendation algorithms have become ubiquitous across commercial fields, from the Amazon \u201cyourstore\u201d splash page to Netflix\u2019s matching % scores. Recommendation algorithms in essence filter large sets of data, i.e. song or [&hellip;]<\/p>\n","protected":false},"author":1003,"featured_media":2457,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"single-custom-post-template.php","format":"standard","meta":{"_et_pb_use_builder":"","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"categories":[67],"tags":[],"class_list":["post-2444","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ml-nlp"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v24.1 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Is There Progress on Neural Recommendation? - Skim AI<\/title>\n<meta name=\"description\" content=\"Machine learning has widespread impact but are we really making progress with neural recommendation algorithms with machine learning?\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/skimai.com\/fr\/algorithmes-de-recommandation-neuronale\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Is There Progress on Neural Recommendation? - Skim AI\" \/>\n<meta property=\"og:description\" content=\"Machine learning has widespread impact but are we really making progress with neural recommendation algorithms with machine learning?\" \/>\n<meta property=\"og:url\" content=\"https:\/\/skimai.com\/fr\/algorithmes-de-recommandation-neuronale\/\" \/>\n<meta property=\"og:site_name\" content=\"Skim AI\" \/>\n<meta property=\"article:published_time\" content=\"2019-10-23T12:42:59+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-05-20T12:38:38+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/skimai.com\/wp-content\/uploads\/2019\/10\/background-beverage-ceramic-2726370.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"5184\" \/>\n\t<meta property=\"og:image:height\" content=\"3456\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Greggory Elias\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u00c9crit par\" \/>\n\t<meta name=\"twitter:data1\" content=\"Greggory Elias\" \/>\n\t<meta name=\"twitter:label2\" content=\"Dur\u00e9e de lecture estim\u00e9e\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/skimai.com\/neural-recommendation-algorithms\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/skimai.com\/neural-recommendation-algorithms\/\"},\"author\":{\"name\":\"Greggory Elias\",\"@id\":\"https:\/\/skimai.com\/uk\/#\/schema\/person\/7a883b4a2d2ea22040f42a7975eb86c6\"},\"headline\":\"Are We Really Making Progress on Neural Recommendation Approaches?\",\"datePublished\":\"2019-10-23T12:42:59+00:00\",\"dateModified\":\"2024-05-20T12:38:38+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/skimai.com\/neural-recommendation-algorithms\/\"},\"wordCount\":18,\"publisher\":{\"@id\":\"https:\/\/skimai.com\/uk\/#organization\"},\"image\":{\"@id\":\"https:\/\/skimai.com\/neural-recommendation-algorithms\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/skimai.com\/wp-content\/uploads\/2019\/10\/background-beverage-ceramic-2726370.jpg\",\"articleSection\":[\"LLMs \/ NLP\"],\"inLanguage\":\"fr-FR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/skimai.com\/neural-recommendation-algorithms\/\",\"url\":\"https:\/\/skimai.com\/neural-recommendation-algorithms\/\",\"name\":\"Is There Progress on Neural Recommendation? - Skim AI\",\"isPartOf\":{\"@id\":\"https:\/\/skimai.com\/uk\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/skimai.com\/neural-recommendation-algorithms\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/skimai.com\/neural-recommendation-algorithms\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/skimai.com\/wp-content\/uploads\/2019\/10\/background-beverage-ceramic-2726370.jpg\",\"datePublished\":\"2019-10-23T12:42:59+00:00\",\"dateModified\":\"2024-05-20T12:38:38+00:00\",\"description\":\"Machine learning has widespread impact but are we really making progress with neural recommendation algorithms with machine learning?\",\"breadcrumb\":{\"@id\":\"https:\/\/skimai.com\/neural-recommendation-algorithms\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/skimai.com\/neural-recommendation-algorithms\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/skimai.com\/neural-recommendation-algorithms\/#primaryimage\",\"url\":\"https:\/\/skimai.com\/wp-content\/uploads\/2019\/10\/background-beverage-ceramic-2726370.jpg\",\"contentUrl\":\"https:\/\/skimai.com\/wp-content\/uploads\/2019\/10\/background-beverage-ceramic-2726370.jpg\",\"width\":5184,\"height\":3456,\"caption\":\"background beverage ceramic 2726370\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/skimai.com\/neural-recommendation-algorithms\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/skimai.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Are We Really Making Progress on Neural Recommendation Approaches?\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/skimai.com\/uk\/#website\",\"url\":\"https:\/\/skimai.com\/uk\/\",\"name\":\"Skim AI\",\"description\":\"The AI Agent Workforce Platform\",\"publisher\":{\"@id\":\"https:\/\/skimai.com\/uk\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/skimai.com\/uk\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"fr-FR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/skimai.com\/uk\/#organization\",\"name\":\"Skim AI\",\"url\":\"https:\/\/skimai.com\/uk\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/skimai.com\/uk\/#\/schema\/logo\/image\/\",\"url\":\"http:\/\/skimai.com\/wp-content\/uploads\/2020\/07\/SKIM-AI-Header-Logo.png\",\"contentUrl\":\"http:\/\/skimai.com\/wp-content\/uploads\/2020\/07\/SKIM-AI-Header-Logo.png\",\"width\":194,\"height\":58,\"caption\":\"Skim AI\"},\"image\":{\"@id\":\"https:\/\/skimai.com\/uk\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.linkedin.com\/company\/skim-ai\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/skimai.com\/uk\/#\/schema\/person\/7a883b4a2d2ea22040f42a7975eb86c6\",\"name\":\"Greggory Elias\",\"url\":\"https:\/\/skimai.com\/fr\/author\/gregg\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"La recommandation neuronale progresse-t-elle ? - Skim AI","description":"L'apprentissage automatique a un impact consid\u00e9rable, mais les algorithmes de recommandation neuronale progressent-ils vraiment gr\u00e2ce \u00e0 l'apprentissage automatique ?","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/skimai.com\/fr\/algorithmes-de-recommandation-neuronale\/","og_locale":"fr_FR","og_type":"article","og_title":"Is There Progress on Neural Recommendation? - Skim AI","og_description":"Machine learning has widespread impact but are we really making progress with neural recommendation algorithms with machine learning?","og_url":"https:\/\/skimai.com\/fr\/algorithmes-de-recommandation-neuronale\/","og_site_name":"Skim AI","article_published_time":"2019-10-23T12:42:59+00:00","article_modified_time":"2024-05-20T12:38:38+00:00","og_image":[{"width":5184,"height":3456,"url":"https:\/\/skimai.com\/wp-content\/uploads\/2019\/10\/background-beverage-ceramic-2726370.jpg","type":"image\/jpeg"}],"author":"Greggory Elias","twitter_card":"summary_large_image","twitter_misc":{"\u00c9crit par":"Greggory Elias","Dur\u00e9e de lecture estim\u00e9e":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/skimai.com\/neural-recommendation-algorithms\/#article","isPartOf":{"@id":"https:\/\/skimai.com\/neural-recommendation-algorithms\/"},"author":{"name":"Greggory Elias","@id":"https:\/\/skimai.com\/uk\/#\/schema\/person\/7a883b4a2d2ea22040f42a7975eb86c6"},"headline":"Are We Really Making Progress on Neural Recommendation Approaches?","datePublished":"2019-10-23T12:42:59+00:00","dateModified":"2024-05-20T12:38:38+00:00","mainEntityOfPage":{"@id":"https:\/\/skimai.com\/neural-recommendation-algorithms\/"},"wordCount":18,"publisher":{"@id":"https:\/\/skimai.com\/uk\/#organization"},"image":{"@id":"https:\/\/skimai.com\/neural-recommendation-algorithms\/#primaryimage"},"thumbnailUrl":"https:\/\/skimai.com\/wp-content\/uploads\/2019\/10\/background-beverage-ceramic-2726370.jpg","articleSection":["LLMs \/ NLP"],"inLanguage":"fr-FR"},{"@type":"WebPage","@id":"https:\/\/skimai.com\/neural-recommendation-algorithms\/","url":"https:\/\/skimai.com\/neural-recommendation-algorithms\/","name":"La recommandation neuronale progresse-t-elle ? - Skim AI","isPartOf":{"@id":"https:\/\/skimai.com\/uk\/#website"},"primaryImageOfPage":{"@id":"https:\/\/skimai.com\/neural-recommendation-algorithms\/#primaryimage"},"image":{"@id":"https:\/\/skimai.com\/neural-recommendation-algorithms\/#primaryimage"},"thumbnailUrl":"https:\/\/skimai.com\/wp-content\/uploads\/2019\/10\/background-beverage-ceramic-2726370.jpg","datePublished":"2019-10-23T12:42:59+00:00","dateModified":"2024-05-20T12:38:38+00:00","description":"L'apprentissage automatique a un impact consid\u00e9rable, mais les algorithmes de recommandation neuronale progressent-ils vraiment gr\u00e2ce \u00e0 l'apprentissage automatique ?","breadcrumb":{"@id":"https:\/\/skimai.com\/neural-recommendation-algorithms\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/skimai.com\/neural-recommendation-algorithms\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/skimai.com\/neural-recommendation-algorithms\/#primaryimage","url":"https:\/\/skimai.com\/wp-content\/uploads\/2019\/10\/background-beverage-ceramic-2726370.jpg","contentUrl":"https:\/\/skimai.com\/wp-content\/uploads\/2019\/10\/background-beverage-ceramic-2726370.jpg","width":5184,"height":3456,"caption":"background beverage ceramic 2726370"},{"@type":"BreadcrumbList","@id":"https:\/\/skimai.com\/neural-recommendation-algorithms\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/skimai.com\/"},{"@type":"ListItem","position":2,"name":"Are We Really Making Progress on Neural Recommendation Approaches?"}]},{"@type":"WebSite","@id":"https:\/\/skimai.com\/uk\/#website","url":"https:\/\/skimai.com\/uk\/","name":"Skim AI","description":"La plateforme de travail des agents de l'IA","publisher":{"@id":"https:\/\/skimai.com\/uk\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/skimai.com\/uk\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"fr-FR"},{"@type":"Organization","@id":"https:\/\/skimai.com\/uk\/#organization","name":"Skim AI","url":"https:\/\/skimai.com\/uk\/","logo":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/skimai.com\/uk\/#\/schema\/logo\/image\/","url":"http:\/\/skimai.com\/wp-content\/uploads\/2020\/07\/SKIM-AI-Header-Logo.png","contentUrl":"http:\/\/skimai.com\/wp-content\/uploads\/2020\/07\/SKIM-AI-Header-Logo.png","width":194,"height":58,"caption":"Skim AI"},"image":{"@id":"https:\/\/skimai.com\/uk\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.linkedin.com\/company\/skim-ai"]},{"@type":"Person","@id":"https:\/\/skimai.com\/uk\/#\/schema\/person\/7a883b4a2d2ea22040f42a7975eb86c6","name":"Greggory Elias","url":"https:\/\/skimai.com\/fr\/author\/gregg\/"}]}},"_links":{"self":[{"href":"https:\/\/skimai.com\/fr\/wp-json\/wp\/v2\/posts\/2444","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/skimai.com\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/skimai.com\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/skimai.com\/fr\/wp-json\/wp\/v2\/users\/1003"}],"replies":[{"embeddable":true,"href":"https:\/\/skimai.com\/fr\/wp-json\/wp\/v2\/comments?post=2444"}],"version-history":[{"count":0,"href":"https:\/\/skimai.com\/fr\/wp-json\/wp\/v2\/posts\/2444\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/skimai.com\/fr\/wp-json\/wp\/v2\/media\/2457"}],"wp:attachment":[{"href":"https:\/\/skimai.com\/fr\/wp-json\/wp\/v2\/media?parent=2444"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/skimai.com\/fr\/wp-json\/wp\/v2\/categories?post=2444"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/skimai.com\/fr\/wp-json\/wp\/v2\/tags?post=2444"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}