{"id":4095,"date":"2024-07-15T16:33:41","date_gmt":"2024-07-15T08:33:41","guid":{"rendered":"https:\/\/nullthought.net\/?p=4095"},"modified":"2024-07-16T12:27:33","modified_gmt":"2024-07-16T04:27:33","slug":"%e8%ae%ad%e7%bb%83ai%e6%a8%a1%e5%9e%8b%e5%b0%b1%e5%83%8f%e6%98%af%e7%82%bc%e4%b8%b9","status":"publish","type":"post","link":"https:\/\/nullthought.net\/?p=4095","title":{"rendered":"\u8bad\u7ec3AI\u6a21\u578b\u5c31\u50cf\u662f\u70bc\u4e39\u2026"},"content":{"rendered":"\n<p>\u8bad\u7ec3AI\u6a21\u578b\u5c31\u50cf\u662f\u70bc\u4e39\u2026\ud83d\ude04<\/p>\n\n\n\n<p>#AI\u6a21\u578b\u8bad\u7ec3 #\u70bc\u4e39<br>\u770b\u516c\u53f8\u5c0f\u4f19\u4f34\u8bad\u7ec3AI\u6a21\u578b\uff0c\u901a\u8fc7\u4f18\u5316\u8f93\u5165\u5c42\u4f8b\u5982\u62c9\u5bbd\u6570\u503c\u65f6\u95f4\u533a\u95f4\u548c\u589e\u52a0\u5178\u578b\u7279\u5f81\u503c\uff0c\u8c03\u6574\u9690\u85cf\u5c42\u5c42\u7ea7\u548c\u6539\u53d8\u90e8\u5206\u5c42\u7684\u7c7b\u578b\uff0c\u6a21\u578b\u7684\u9a8c\u8bc1\u7cbe\u5ea6\u63d0\u5347\u4e8630\u591a\u4e2a\u767e\u5206\u70b9\u3002<\/p>\n\n\n\n<p>#\u70bc\u4e39\u2697\ufe0f\u6301\u7eed\u4e2d~<br>\u516c\u53f8\u5c0f\u4f19\u4f34\u62a5\u544a\uff0c\u670d\u52a1\u5668\u7aefAI\u6a21\u578b\u7ecf\u8fc7\u4f4e\u4f4d\u6574\u578b\u5316\u5904\u7406\u540e\uff0c\u8fd0\u884c\u6548\u7387\u63d0\u5347\u6570\u5341\u500d\uff0c\u63a8\u7406\u7cbe\u5ea6\u4ec5\u964d\u4f4e\u7ea63%\uff0c\u53d1\u5e03\u5230\u8f83\u4f4e\u7b97\u529b\u8fb9\u7f18\u8bbe\u5907\u4e0a\u6d4b\u8bd5\u8fd0\u884c\u826f\u597d\uff0c\u57fa\u672c\u8fbe\u5230\u9884\u671f\u76ee\u6807\u3002\ud83e\uddd9\ud83d\udd2e<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"1024\" src=\"https:\/\/nullthought.net\/wp-content\/uploads\/2024\/07\/The-process-of-training-an-AI-model-is-like-refining-alchemy.jpg\" alt=\"\" class=\"wp-image-4096\" srcset=\"https:\/\/nullthought.net\/wp-content\/uploads\/2024\/07\/The-process-of-training-an-AI-model-is-like-refining-alchemy.jpg 1024w, https:\/\/nullthought.net\/wp-content\/uploads\/2024\/07\/The-process-of-training-an-AI-model-is-like-refining-alchemy-300x300.jpg 300w, https:\/\/nullthought.net\/wp-content\/uploads\/2024\/07\/The-process-of-training-an-AI-model-is-like-refining-alchemy-150x150.jpg 150w, https:\/\/nullthought.net\/wp-content\/uploads\/2024\/07\/The-process-of-training-an-AI-model-is-like-refining-alchemy-768x768.jpg 768w, https:\/\/nullthought.net\/wp-content\/uploads\/2024\/07\/The-process-of-training-an-AI-model-is-like-refining-alchemy-120x120.jpg 120w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\">\u8bad\u7ec3AI\u6a21\u578b\u5c31\u50cf\u662f\u70bc\u4e39\u2026\u2697\ufe0f<\/figcaption><\/figure>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<p>Training an AI model is just like refining alchemy&#8230;\ud83d\ude04<\/p>\n\n\n\n<p>#AIModelTraining #Alchemy<br>Train AI models by optimizing the input layer, such as widening the TSD time range and adding typical feature values, adjusting the hierarchy of hidden layers, and changing the types of some layers, the validation accuracy of the model increased by more than 30 percentage points.<\/p>\n\n\n\n<p>#Alchemy\u2697\ufe0fContinues~<br>After processing the server-side AI model with low-bit integer quantization, the running efficiency improved by dozens of times, with inference accuracy reduced by only about 3%. When deployed to edge devices with low computing power, it performed well, basically achieving the expected goals.\ud83e\uddd9\ud83d\udd2e<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"1024\" src=\"https:\/\/nullthought.net\/wp-content\/uploads\/2024\/07\/Training_an_AI_model_is_like_refining_alchemy._Pixar-style.jpg\" alt=\"\" class=\"wp-image-4097\" srcset=\"https:\/\/nullthought.net\/wp-content\/uploads\/2024\/07\/Training_an_AI_model_is_like_refining_alchemy._Pixar-style.jpg 1024w, https:\/\/nullthought.net\/wp-content\/uploads\/2024\/07\/Training_an_AI_model_is_like_refining_alchemy._Pixar-style-300x300.jpg 300w, https:\/\/nullthought.net\/wp-content\/uploads\/2024\/07\/Training_an_AI_model_is_like_refining_alchemy._Pixar-style-150x150.jpg 150w, https:\/\/nullthought.net\/wp-content\/uploads\/2024\/07\/Training_an_AI_model_is_like_refining_alchemy._Pixar-style-768x768.jpg 768w, https:\/\/nullthought.net\/wp-content\/uploads\/2024\/07\/Training_an_AI_model_is_like_refining_alchemy._Pixar-style-120x120.jpg 120w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\"><strong>Training an AI model is like refining alchemy<\/strong>&#8230;\u2697\ufe0f<\/figcaption><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>\u8bad\u7ec3AI\u6a21\u578b\u5c31\u50cf\u662f\u70bc\u4e39\u2026\ud83d\ude04 #AI\u6a21\u578b\u8bad\u7ec3 #\u70bc\u4e39\u770b\u516c\u53f8\u5c0f\u4f19\u4f34\u8bad\u7ec3AI\u6a21\u578b\uff0c\u901a\u8fc7\u4f18\u5316\u8f93\u5165\u5c42\u4f8b\u5982\u62c9\u5bbd\u6570\u503c\u65f6\u95f4\u533a\u95f4 [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","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":"","ast-disable-related-posts":"","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":"set","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"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":""},"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-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":"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":""},"mobile":{"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":""}},"footnotes":""},"categories":[8],"tags":[39,23],"class_list":["post-4095","post","type-post","status-publish","format-standard","hentry","category-tech","tag-ai","tag-random-talks"],"rttpg_featured_image_url":null,"rttpg_author":{"display_name":"NullThought","author_link":"https:\/\/nullthought.net\/?author=1"},"rttpg_comment":0,"rttpg_category":"<a href=\"https:\/\/nullthought.net\/?cat=8\" rel=\"category\">Tech<\/a>","rttpg_excerpt":"\u8bad\u7ec3AI\u6a21\u578b\u5c31\u50cf\u662f\u70bc\u4e39\u2026\ud83d\ude04 #AI\u6a21\u578b\u8bad\u7ec3 #\u70bc\u4e39\u770b\u516c\u53f8\u5c0f\u4f19\u4f34\u8bad\u7ec3AI\u6a21\u578b\uff0c\u901a\u8fc7\u4f18\u5316\u8f93\u5165\u5c42\u4f8b\u5982\u62c9\u5bbd\u6570\u503c\u65f6\u95f4\u533a\u95f4&hellip;","_links":{"self":[{"href":"https:\/\/nullthought.net\/index.php?rest_route=\/wp\/v2\/posts\/4095","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/nullthought.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/nullthought.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/nullthought.net\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/nullthought.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=4095"}],"version-history":[{"count":3,"href":"https:\/\/nullthought.net\/index.php?rest_route=\/wp\/v2\/posts\/4095\/revisions"}],"predecessor-version":[{"id":4103,"href":"https:\/\/nullthought.net\/index.php?rest_route=\/wp\/v2\/posts\/4095\/revisions\/4103"}],"wp:attachment":[{"href":"https:\/\/nullthought.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4095"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/nullthought.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4095"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/nullthought.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4095"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}