{"id":4664,"date":"2026-08-12T16:59:59","date_gmt":"2026-08-12T14:59:59","guid":{"rendered":"https:\/\/ellistat.com\/?post_type=guide-dutilisateur&p=4664"},"modified":"2026-08-12T16:59:59","modified_gmt":"2026-08-12T14:59:59","slug":"filling-plan","status":"publish","type":"guide-dutilisateur","link":"https:\/\/ellistat.com\/en\/guide-dutilisateur\/plan-de-remplissage\/","title":{"rendered":"Filling plan"},"content":{"rendered":"

The previous plans all aim to estimate a\u00a0given model<\/strong>\u00a0\u2014 linear, with interactions, quadratic. Filling schemes have a different purpose:\u00a0cover the experimental area evenly<\/strong>, without assuming the form of the answer.<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

This is the approach taken by machine learning models, which learn the shape rather than assuming it. The factors must be quantitative<\/strong>, you need some at least two<\/strong> and no more than 20<\/strong>.<\/p>\n\n\n\n

1. Calculated chart or tabulated table<\/h2>\n\n\n\n

The list of possible layouts includes two categories:<\/p>\n\n\n\n

    \n
  • Ellistat Map (calculated)<\/strong>, the first option offered and selected by default: the only one whose number of attempts and criteria match your configuration; ; <\/li>\n\n\n\n
  • Visit\u00a0tabulated tables<\/strong>, with a fixed number of trials: Audze-Eglais (9, 15, 16, 25, 50, 100 trials depending on the number of factors), Latin Hypercube Design (16, 25, 50), and NOLH 17. For more than 10 factors, none of these designs remain viable; only the calculated design is suitable.<\/li>\n<\/ul>\n\n\n\n

    2. Settings for the calculated plan<\/h2>\n\n\n\n
    Adjustment<\/strong><\/td>Role<\/strong><\/td><\/tr><\/thead>
    Number of factors<\/strong><\/td>Reminder: read-only.<\/td><\/tr>
    Number of trials<\/strong><\/td>At a minimum k<\/em>+1, up to 100. The default value is five trials per factor, with a minimum of 9.<\/td><\/tr>
    Hypothesis on the factors<\/strong><\/td>\u00abAll factors are active\u00bb or \u00abOnly a few factors are active.\u00bb.<\/td><\/tr>
    Limiting Correlation<\/strong><\/td>Enforces maximum correlation between factors. Enabled by default.<\/td><\/tr>
    Maximum correlation |r|<\/strong><\/td>The target is 0.03 by default.<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n

    The selected hypothesis is explained on the screen, and the choice matters:<\/p>\n\n\n\n

      \n
    • All factors are active<\/strong>\u00a0: Audze-Eglais criterion alone: complete space filling. To be selected if the downstream model uses all factors; ;<\/li>\n\n\n\n
    • Only a few factors are active<\/strong>\u00a0: Audze-Eglais + MaxPro: also meets expectations in situations where the outcome depends on just two or three factors.<\/li>\n<\/ul>\n\n\n\n

      \ud83d\udca1 This is the setting that really distinguishes between the two fill patterns, and it\u2019s determined by considering\u00a0the next step<\/strong>. If you suspect that two out of eight factors account for the bulk of the variation, a plane that fits the eight-dimensional space well may project very poorly onto the plane of those two factors; the points overlap on that plane, and the model can hardly distinguish anything there. This is precisely what the MaxPro term corrects.<\/p>\n\n\n\n

      \u26a0\ufe0f The correlation barrier is recommended: the MaxPro term significantly degrades correlations when it is not used. Disabling it only makes sense if you want maximum filling without worrying about the independence of the effects.<\/p>\n\n\n\n

      3. Calculate and read the result<\/h2>\n\n\n\n

      The button Calculate<\/strong> Start the annealing process in a worker, with a progress bar and a button Stop<\/strong>. The resulting plan is saved in the experiment plan: it remains intact even after navigation.<\/p>\n\n\n\n

      Three indicators appear next to the button:<\/p>\n\n\n\n

      \"\"<\/figure>\n\n\n\n
        \n
      • Audze-Eglais<\/strong>\u00a0: the fill factor\u2014the lower it is, the better the area is covered; ; <\/li>\n\n\n\n
      • MaxPro<\/strong>\u00a0: the projection fulfillment criterion, displayed when the \u00aba few active factors\u00bb assumption is selected; ;<\/li>\n\n\n\n
      • Max |r|<\/strong>\u00a0: the strongest absolute correlation between two factors.<\/li>\n<\/ul>\n\n\n\n

        The button\u00a0Correlation matrix<\/strong>\u00a0poster:\u00a0<\/p>\n\n\n\n

        <\/p>\n\n\n\n

        The button\u00a0Point clouds<\/strong>\u00a0offers two complementary interpretations: <\/p>\n\n\n\n

          \n
        • the matrix of the\u00a0correlations between factors<\/strong>, on a fixed scale from \u22121 to +1 \u2014 a well-optimized plan therefore appears nearly neutral, which is correct <\/li>\n\n\n\n
        • and the\u00a0scatter plots by factor pairs<\/strong>, which show\u00a0why<\/em>\u00a0A weak correlation: points are well spread out, or there is a diagonal pattern.<\/li>\n<\/ul>\n\n\n\n
          \"\"<\/figure>\n\n\n\n

          \ud83d\udca1 The fixed scale of the matrix is not a configuration error. A scale adjusted to the data would display correlations of a few hundredths in bright colors, giving the false impression of a poor plot. Here, a nearly orthogonal plot is clearly visible as such.<\/p>\n\n\n\n

          \u26a0\ufe0f The button D-Optimal<\/strong> is intentionally omitted from filling plans: searching for a D-optimal subset of a filling plan is meaningless, since the plan aims to cover the space rather than to estimate a given model.<\/p>","protected":false},"featured_media":0,"menu_order":100,"template":"","meta":{"_acf_changed":true},"menu-guide-dutilisateur":[24],"class_list":["post-4664","guide-dutilisateur","type-guide-dutilisateur","status-publish","hentry","menu-guide-dutilisateur-7-doe-plans-dexperiences"],"acf":[],"yoast_head":"\nPlan de remplissage - Ellistat<\/title>\n<meta name=\"description\" content=\"Latin Hypercube, Audze-Eglais, MaxPro : construisez un plan de remplissage d'espace optimis\u00e9 pour entra\u00eener vos mod\u00e8les de machine learning sans hypoth\u00e8se a priori.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/ellistat.com\/en\/users-guide\/filling-plan\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Plan de remplissage - Ellistat\" \/>\n<meta property=\"og:description\" content=\"Latin Hypercube, Audze-Eglais, MaxPro : construisez un plan de remplissage d'espace optimis\u00e9 pour entra\u00eener vos mod\u00e8les de machine learning sans hypoth\u00e8se a priori.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/ellistat.com\/en\/users-guide\/filling-plan\/\" \/>\n<meta property=\"og:site_name\" content=\"Ellistat\" \/>\n<meta property=\"og:image\" content=\"https:\/\/ellistat.com\/wp-content\/uploads\/remplissage.png\" \/>\n\t<meta property=\"og:image:width\" content=\"644\" \/>\n\t<meta property=\"og:image:height\" content=\"298\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/ellistat.com\\\/guide-dutilisateur\\\/plan-de-remplissage\\\/\",\"url\":\"https:\\\/\\\/ellistat.com\\\/guide-dutilisateur\\\/plan-de-remplissage\\\/\",\"name\":\"Plan de remplissage - Ellistat\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/ellistat.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/ellistat.com\\\/guide-dutilisateur\\\/plan-de-remplissage\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/ellistat.com\\\/guide-dutilisateur\\\/plan-de-remplissage\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/ellistat.com\\\/wp-content\\\/uploads\\\/remplissage.png\",\"datePublished\":\"2026-08-12T14:59:59+00:00\",\"description\":\"Latin Hypercube, Audze-Eglais, MaxPro : construisez un plan de remplissage d'espace optimis\u00e9 pour entra\u00eener vos mod\u00e8les de machine learning sans hypoth\u00e8se a priori.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/ellistat.com\\\/guide-dutilisateur\\\/plan-de-remplissage\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/ellistat.com\\\/guide-dutilisateur\\\/plan-de-remplissage\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/ellistat.com\\\/guide-dutilisateur\\\/plan-de-remplissage\\\/#primaryimage\",\"url\":\"https:\\\/\\\/ellistat.com\\\/wp-content\\\/uploads\\\/remplissage.png\",\"contentUrl\":\"https:\\\/\\\/ellistat.com\\\/wp-content\\\/uploads\\\/remplissage.png\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/ellistat.com\\\/guide-dutilisateur\\\/plan-de-remplissage\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Accueil\",\"item\":\"https:\\\/\\\/ellistat.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Plan de remplissage\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/ellistat.com\\\/#website\",\"url\":\"https:\\\/\\\/ellistat.com\\\/\",\"name\":\"Ellistat\",\"description\":\"La suite qualit\u00e9 de l'industrie m\u00e9canique\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/ellistat.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Filling plan - Ellistat","description":"Latin Hypercube, Audze-Eglais, MaxPro: Build an optimized space-filling scheme to train your machine learning models without any prior assumptions.","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:\/\/ellistat.com\/en\/users-guide\/filling-plan\/","og_locale":"en_US","og_type":"article","og_title":"Plan de remplissage - Ellistat","og_description":"Latin Hypercube, Audze-Eglais, MaxPro : construisez un plan de remplissage d'espace optimis\u00e9 pour entra\u00eener vos mod\u00e8les de machine learning sans hypoth\u00e8se a priori.","og_url":"https:\/\/ellistat.com\/en\/users-guide\/filling-plan\/","og_site_name":"Ellistat","og_image":[{"width":644,"height":298,"url":"https:\/\/ellistat.com\/wp-content\/uploads\/remplissage.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/ellistat.com\/guide-dutilisateur\/plan-de-remplissage\/","url":"https:\/\/ellistat.com\/guide-dutilisateur\/plan-de-remplissage\/","name":"Filling plan - Ellistat","isPartOf":{"@id":"https:\/\/ellistat.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/ellistat.com\/guide-dutilisateur\/plan-de-remplissage\/#primaryimage"},"image":{"@id":"https:\/\/ellistat.com\/guide-dutilisateur\/plan-de-remplissage\/#primaryimage"},"thumbnailUrl":"https:\/\/ellistat.com\/wp-content\/uploads\/remplissage.png","datePublished":"2026-08-12T14:59:59+00:00","description":"Latin Hypercube, Audze-Eglais, MaxPro: Build an optimized space-filling scheme to train your machine learning models without any prior assumptions.","breadcrumb":{"@id":"https:\/\/ellistat.com\/guide-dutilisateur\/plan-de-remplissage\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/ellistat.com\/guide-dutilisateur\/plan-de-remplissage\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/ellistat.com\/guide-dutilisateur\/plan-de-remplissage\/#primaryimage","url":"https:\/\/ellistat.com\/wp-content\/uploads\/remplissage.png","contentUrl":"https:\/\/ellistat.com\/wp-content\/uploads\/remplissage.png"},{"@type":"BreadcrumbList","@id":"https:\/\/ellistat.com\/guide-dutilisateur\/plan-de-remplissage\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Accueil","item":"https:\/\/ellistat.com\/"},{"@type":"ListItem","position":2,"name":"Plan de remplissage"}]},{"@type":"WebSite","@id":"https:\/\/ellistat.com\/#website","url":"https:\/\/ellistat.com\/","name":"Ellistat","description":"The quality suite for the mechanical engineering industry","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/ellistat.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/ellistat.com\/en\/wp-json\/wp\/v2\/guide-dutilisateur\/4664","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ellistat.com\/en\/wp-json\/wp\/v2\/guide-dutilisateur"}],"about":[{"href":"https:\/\/ellistat.com\/en\/wp-json\/wp\/v2\/types\/guide-dutilisateur"}],"wp:attachment":[{"href":"https:\/\/ellistat.com\/en\/wp-json\/wp\/v2\/media?parent=4664"}],"wp:term":[{"taxonomy":"menu-guide-dutilisateur","embeddable":true,"href":"https:\/\/ellistat.com\/en\/wp-json\/wp\/v2\/menu-guide-dutilisateur?post=4664"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}