{"id":154453,"date":"2023-01-05T14:23:02","date_gmt":"2023-01-05T20:23:02","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2023\/01\/the-physics-principle-that-inspired-modern-ai-art"},"modified":"2023-01-05T14:23:02","modified_gmt":"2023-01-05T20:23:02","slug":"the-physics-principle-that-inspired-modern-ai-art","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2023\/01\/the-physics-principle-that-inspired-modern-ai-art","title":{"rendered":"The Physics Principle That Inspired Modern AI Art"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/the-physics-principle-that-inspired-modern-ai-art3.jpg\"><\/a><\/p>\n<p>The first important generative models for images used an approach to artificial intelligence called a neural network \u2014 a program composed of many layers of computational units called artificial neurons. But even as the quality of their images got better, the models proved unreliable and hard to train. Meanwhile, a powerful generative model \u2014 created by a postdoctoral researcher with a passion for physics \u2014 lay dormant, until two graduate students made technical breakthroughs that brought the beast to life.<\/p>\n<p>DALL\u00b7E 2 is such a beast. The key insight that makes DALL\u00b7E 2\u2019s images possible \u2014 as well as those of its competitors Stable Diffusion and Imagen \u2014 comes from the world of physics. The system that underpins them, known as a diffusion model, is heavily inspired by nonequilibrium thermodynamics, which governs phenomena like the spread of fluids and gases. \u201cThere are a lot of techniques that were initially invented by physicists and now are very important in machine learning,\u201d said <a href=\"https:\/\/yang-song.net\/\">Yang Song<\/a>, a machine learning researcher at OpenAI.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The first important generative models for images used an approach to artificial intelligence called a neural network \u2014 a program composed of many layers of computational units called artificial neurons. But even as the quality of their images got better, the models proved unreliable and hard to train. Meanwhile, a powerful generative model \u2014 created [\u2026]<\/p>\n","protected":false},"author":511,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[219,6],"tags":[],"class_list":["post-154453","post","type-post","status-publish","format-standard","hentry","category-physics","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/154453","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/511"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=154453"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/154453\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=154453"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=154453"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=154453"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}