{"id":4445,"date":"2024-08-26T12:03:32","date_gmt":"2024-08-26T04:03:32","guid":{"rendered":"https:\/\/nullthought.net\/?p=4445"},"modified":"2024-08-26T13:16:19","modified_gmt":"2024-08-26T05:16:19","slug":"ai-feynman%ef%bc%9a%e4%b8%80%e7%a7%8d%e5%8f%97%e7%89%a9%e7%90%86%e5%90%af%e5%8f%91%e7%9a%84%e7%ac%a6%e5%8f%b7%e5%9b%9e%e5%bd%92%e6%96%b9%e6%b3%95","status":"publish","type":"post","link":"https:\/\/nullthought.net\/?p=4445","title":{"rendered":"AI Feynman\uff1a\u4e00\u79cd\u53d7\u7269\u7406\u542f\u53d1\u7684\u7b26\u53f7\u56de\u5f52\u65b9\u6cd5"},"content":{"rendered":"\n

\u7b26\u53f7\u56de\u5f52\uff08Symbolic Regression\uff09\u5728\u5386\u53f2\u4e0a\u5177\u6709\u91cd\u8981\u610f\u4e49\uff0c\u5176\u6839\u6e90\u53ef\u4ee5\u8ffd\u6eaf\u5230\u5f00\u666e\u52d2\u53d1\u73b0\u884c\u661f\u8fd0\u52a8\u5b9a\u5f8b\u3002\u73b0\u4ee3\u7b26\u53f7\u56de\u5f52\u65b9\u6cd5\u5305\u62ec\u9057\u4f20\u7b97\u6cd5\uff0c\u8fd9\u79cd\u7b97\u6cd5\u901a\u8fc7\u6a21\u4eff\u751f\u7269\u8fdb\u5316\u8fc7\u7a0b\u6765\u5bfb\u627e\u6700\u7b26\u5408\u7684\u7b26\u53f7\u8868\u8fbe\u5f0f\u3002<\/p>\n\n\n\n

\u8bba\u6587\u300aAI Feynman\uff1a\u4e00\u79cd\u53d7\u7269\u7406\u542f\u53d1\u7684\u7b26\u53f7\u56de\u5f52\u65b9\u6cd5\u300b\uff08AI Feynman: a Physics-Inspired Method for Symbolic Regression<\/a><\/strong>\uff09\u63a2\u8ba8\u4e86\u7b26\u53f7\u56de\u5f52\u7684\u6311\u6218\uff0c\u8fd9\u6d89\u53ca\u627e\u5230\u4e0e\u672a\u77e5\u51fd\u6570\u6570\u636e\u5339\u914d\u7684\u7b26\u53f7\u8868\u8fbe\u5f0f\u3002\u867d\u7136\u8fd9\u4e00\u95ee\u9898\u5728\u7406\u8bba\u4e0a\u88ab\u8ba4\u4e3a\u662fNP\u96be\u95ee\u9898\uff0c\u4f46\u8bb8\u591a\u5b9e\u9645\u4e2d\u6709\u7528\u7684\u51fd\u6570\u5c55\u793a\u51fa\u5bf9\u79f0\u6027\u3001\u53ef\u5206\u79bb\u6027\u548c\u7ec4\u5408\u6027\u7b49\u6027\u8d28\uff0c\u53ef\u4ee5\u7b80\u5316\u95ee\u9898\u3002\u4f5c\u8005\u63d0\u51fa\u4e86AI Feynman\u7b97\u6cd5\uff0c\u8fd9\u662f\u4e00\u79cd\u9012\u5f52\u7684\u3001\u591a\u7ef4\u5ea6\u7684\u7b26\u53f7\u56de\u5f52\u65b9\u6cd5\uff0c\u5229\u7528\u4e86\u8fd9\u4e9b\u7b80\u5316\u7279\u6027\u3002AI Feynman \u662f\u7b26\u53f7\u56de\u5f52\u7684\u4e00\u4e2a\u5f3a\u5927\u5de5\u5177\uff0c\u7279\u522b\u9002\u7528\u4e8e\u53d7\u7269\u7406\u542f\u53d1\u7684\u95ee\u9898\u3002\u901a\u8fc7\u5c06\u795e\u7ecf\u7f51\u7edc\u4e0e\u57fa\u4e8e\u7269\u7406\u7684\u7b56\u7565\u76f8\u7ed3\u5408\uff0c\u8be5\u7b97\u6cd5\u80fd\u591f\u89e3\u51b3\u4e4b\u524d\u65b9\u6cd5\u65e0\u6cd5\u89e3\u51b3\u7684\u590d\u6742\u65b9\u7a0b\u3002\u8fd9\u79cd\u65b9\u6cd5\u4e0d\u4ec5\u63d0\u9ad8\u4e86\u7b26\u53f7\u56de\u5f52\u7684\u6280\u672f\u6c34\u5e73\uff0c\u8fd8\u4e3a\u7269\u7406\u5b66\u548c\u5176\u4ed6\u79d1\u5b66\u9886\u57df\u7684\u81ea\u52a8\u5316\u53d1\u73b0\u5f00\u8f9f\u4e86\u65b0\u7684\u53ef\u80fd\u6027\u3002<\/p>\n\n\n\n

\u8bba\u6587\u4f5c\u8005\u4e3a\u6765\u81eaMIT\u7684Silviu-Marian Udrescu<\/a>\u548cMax Tegmark<\/a>\u3002<\/p>\n\n\n\n

\u4e00\u3001AI Feynman \u7b97\u6cd5<\/h5>\n\n\n\n

AI Feynman\u7b97\u6cd5\u7684\u6838\u5fc3\u662f\u7ed3\u5408\u795e\u7ecf\u7f51\u7edc\u62df\u5408\u4e0e\u53d7\u7269\u7406\u542f\u53d1\u7684\u6280\u672f\u3002\u8be5\u7b97\u6cd5\u8fed\u4ee3\u5730\u5e94\u7528\u516d\u4e2a\u4e3b\u8981\u7b56\u7565\uff1a<\/p>\n\n\n\n

    \n
  1. \u91cf\u7eb2\u5206\u6790<\/strong>\uff08Dimensional Analysis\uff09\uff1a\u901a\u8fc7\u8981\u6c42\u65b9\u7a0b\u4e24\u8fb9\u7684\u5355\u4f4d\u5339\u914d\u6765\u7b80\u5316\u95ee\u9898\uff0c\u901a\u5e38\u51cf\u5c11\u53d8\u91cf\u6570\u91cf\u3002<\/li>\n\n\n\n
  2. \u591a\u9879\u5f0f\u62df\u5408<\/strong>\uff08Polynomial Fit\uff09\uff1a\u5c1d\u8bd5\u5c06\u6570\u636e\u62df\u5408\u5230\u4f4e\u9636\u591a\u9879\u5f0f\u4e0a\uff0c\u5982\u679c\u51fd\u6570\u5177\u6709\u8fd9\u79cd\u5f62\u5f0f\uff0c\u8fd9\u79cd\u65b9\u6cd5\u975e\u5e38\u76f4\u63a5\u3002<\/li>\n\n\n\n
  3. \u66b4\u529b\u641c\u7d22<\/strong>\uff08Brute Force\uff09\uff1a\u5c1d\u8bd5\u6240\u6709\u53ef\u80fd\u7684\u7b26\u53f7\u8868\u8fbe\u5f0f\uff0c\u6309\u590d\u6742\u6027\u9012\u589e\u7684\u987a\u5e8f\u6392\u5217\u3002<\/li>\n\n\n\n
  4. \u795e\u7ecf\u7f51\u7edc\u62df\u5408<\/strong>\uff08Neural Network Fitting\uff09\uff1a\u8bad\u7ec3\u4e00\u4e2a\u795e\u7ecf\u7f51\u7edc\uff0c\u6839\u636e\u8f93\u5165\u9884\u6d4b\u8f93\u51fa\uff0c\u4ece\u800c\u53d1\u73b0\u51fd\u6570\u4e2d\u7684\u9690\u85cf\u5c5e\u6027\uff0c\u5982\u5bf9\u79f0\u6027\u6216\u53ef\u5206\u79bb\u6027\u3002<\/li>\n\n\n\n
  5. \u5bf9\u79f0\u6027\u68c0\u6d4b<\/strong>\uff08Symmetry Detection\uff09\uff1a\u5229\u7528\u795e\u7ecf\u7f51\u7edc\u68c0\u6d4b\u51fd\u6570\u662f\u5426\u5177\u6709\u5e73\u79fb\u6216\u7f29\u653e\u5bf9\u79f0\u6027\uff0c\u5141\u8bb8\u7b80\u5316\u95ee\u9898\u3002<\/li>\n\n\n\n
  6. \u53ef\u5206\u79bb\u6027\u68c0\u6d4b<\/strong>\uff08Separability Detection\uff09\uff1a\u7b97\u6cd5\u6d4b\u8bd5\u51fd\u6570\u662f\u5426\u53ef\u4ee5\u5199\u6210\u4e24\u4e2a\u66f4\u7b80\u5355\u51fd\u6570\u7684\u4e58\u79ef\u6216\u548c\uff0c\u6bcf\u4e2a\u51fd\u6570\u4f9d\u8d56\u4e8e\u53d8\u91cf\u7684\u4e00\u4e2a\u5b50\u96c6\u3002<\/li>\n<\/ol>\n\n\n\n
    \u4e8c\u3001\u5b9e\u73b0\u4e0e\u7ed3\u679c<\/h5>\n\n\n\n

    \u8be5\u7b97\u6cd5\u5728\u7531\u8d39\u66fc\u7269\u7406\u5b66\u8bb2\u4e49\u4e2d\u7684100\u4e2a\u65b9\u7a0b\u7ec4\u6210\u7684\u6570\u636e\u5e93\u4e0a\u8fdb\u884c\u4e86\u6d4b\u8bd5\uff0c\u6210\u529f\u53d1\u73b0\u4e86\u6240\u6709\u8fd9\u4e9b\u65b9\u7a0b\uff0c\u8868\u73b0\u4f18\u4e8e\u73b0\u6709\u7684\u7b26\u53f7\u56de\u5f52\u8f6f\u4ef6\u5982Eureqa\uff08\u540e\u8005\u4ec5\u89e3\u51b3\u4e8671\u4e2a\u65b9\u7a0b\uff09\u3002\u5bf9\u4e8e\u66f4\u5177\u6311\u6218\u6027\u7684\u57fa\u4e8e\u7269\u7406\u7684\u6d4b\u8bd5\u96c6\uff0cAI Feynman\u5c06\u6210\u529f\u7387\u4ece15%\u63d0\u9ad8\u5230\u4e8690%\u3002<\/p>\n\n\n\n

    \u4e09\u3001\u8be6\u7ec6\u793a\u4f8b<\/h5>\n\n\n\n

    \u8bba\u6587\u8be6\u7ec6\u5c55\u793a\u4e86AI Feynman\u5982\u4f55\u53d1\u73b0\u5f15\u529b\u516c\u5f0f\u7684\u8fc7\u7a0b\u3002\u8be5\u8fc7\u7a0b\u6d89\u53ca\u591a\u4e2a\u6b65\u9aa4\uff0c\u5305\u62ec\u91cf\u7eb2\u5206\u6790\u4ee5\u51cf\u5c11\u53d8\u91cf\u6570\u91cf\uff0c\u4f7f\u7528\u795e\u7ecf\u7f51\u7edc\u62df\u5408\u4ee5\u8bc6\u522b\u5bf9\u79f0\u6027\uff0c\u4ee5\u53ca\u591a\u9879\u5f0f\u62df\u5408\u6765\u89e3\u51b3\u7b80\u5316\u540e\u7684\u65b9\u7a0b\u3002<\/p>\n\n\n\n

    \u56db\u3001\u65b9\u6cd5\u8bba<\/h5>\n\n\n\n

    \u4f5c\u8005\u8be6\u7ec6\u4ecb\u7ecd\u4e86AI Feynman\u7b97\u6cd5\u4e2d\u4f7f\u7528\u7684\u516d\u4e2a\u7b56\u7565\u3002\u8fd9\u4e9b\u7b56\u7565\u65e8\u5728\u5229\u7528\u7269\u7406\u5b66\u4e2d\u51fd\u6570\u7684\u5e38\u89c1\u7279\u6027\uff0c\u4f8b\u5982\u5df2\u77e5\u5355\u4f4d\u3001\u4f4e\u9636\u591a\u9879\u5f0f\u3001\u7ec4\u5408\u6027\u3001\u5e73\u6ed1\u6027\u3001\u5bf9\u79f0\u6027\u548c\u53ef\u5206\u79bb\u6027\u3002\u6bcf\u4e2a\u7b56\u7565\u4f5c\u4e3a\u7b97\u6cd5\u4e2d\u7684\u4e00\u4e2a\u6a21\u5757\u6765\u5b9e\u73b0\uff0c\u7b97\u6cd5\u4f1a\u8fed\u4ee3\u5730\u5e94\u7528\u8fd9\u4e9b\u6a21\u5757\uff0c\u8f6c\u6362\u5e76\u7b80\u5316\u95ee\u9898\uff0c\u76f4\u5230\u627e\u5230\u89e3\u51b3\u65b9\u6848\u3002<\/p>\n\n\n\n

    \u4e94\u3001\u8ba8\u8bba\u4e0e\u672a\u6765\u5de5\u4f5c<\/h5>\n\n\n\n

    \u4f5c\u8005\u8ba8\u8bba\u4e86\u4ed6\u4eec\u65b9\u6cd5\u7684\u5c40\u9650\u6027\uff0c\u7279\u522b\u662f\u5728\u5904\u7406\u5177\u6709\u590d\u6742\u6216\u4e0d\u5e38\u89c1\u7279\u6027\u7684\u51fd\u6570\u65f6\u3002\u4ed6\u4eec\u63d0\u51fa\u4e86\u6f5c\u5728\u7684\u6539\u8fdb\u65b9\u5411\uff0c\u4f8b\u5982\u66f4\u597d\u5730\u5c06\u66b4\u529b\u65b9\u6cd5\u4e0e\u795e\u7ecf\u7f51\u7edc\u641c\u7d22\u9690\u85cf\u7b80\u5316\u7ed3\u5408\u8d77\u6765\uff0c\u4ee5\u53ca\u66f4\u590d\u6742\u5730\u4f7f\u7528\u795e\u7ecf\u7f51\u7edc\u6765\u51cf\u5c11\u62df\u5408\u566a\u58f0\u3002<\/p>\n\n\n\n

    \u516d\u3001\u7ed3\u8bba<\/h5>\n\n\n\n

    \u8bba\u6587\u603b\u7ed3\u4e86AI Feynman\u5728\u7b26\u53f7\u56de\u5f52\u9886\u57df\u7684\u663e\u8457\u8fdb\u5c55\uff0c\u5c24\u5176\u662f\u5728\u53d7\u7269\u7406\u542f\u53d1\u7684\u95ee\u9898\u4e2d\u3002\u4f5c\u8005\u9884\u6d4b\uff0c\u8fdb\u4e00\u6b65\u7684\u6539\u8fdb\u53ef\u80fd\u4f1a\u4f7f\u8ba1\u7b97\u673a\u9996\u6b21\u901a\u8fc7\u7b26\u53f7\u56de\u5f52\u53d1\u73b0\u65b0\u7684\u3001\u6709\u7528\u7684\u7269\u7406\u516c\u5f0f\uff0c\u8fd9\u5c06\u662f\u8be5\u9886\u57df\u7684\u4e00\u4e2a\u91cd\u5927\u91cc\u7a0b\u7891\u3002<\/p>\n\n\n\n

    \n\n\n\n

    AI Feynman on GitHub: https:\/\/github.com\/SJ001\/AI-Feynman<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

    \u7b26\u53f7\u56de\u5f52\uff08Symbolic Regression\uff09\u5728\u5386\u53f2\u4e0a\u5177\u6709\u91cd\u8981\u610f\u4e49\uff0c\u5176\u6839\u6e90\u53ef\u4ee5\u8ffd\u6eaf\u5230\u5f00\u666e\u52d2\u53d1\u73b0\u884c\u661f\u8fd0\u52a8\u5b9a\u5f8b […]<\/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":[36],"tags":[39,48,71],"class_list":["post-4445","post","type-post","status-publish","format-standard","hentry","category-36","tag-ai","tag-48","tag-physics"],"rttpg_featured_image_url":null,"rttpg_author":{"display_name":"NullThought","author_link":"https:\/\/nullthought.net\/?author=1"},"rttpg_comment":0,"rttpg_category":"\u79d1\u5b66<\/a>","rttpg_excerpt":"\u7b26\u53f7\u56de\u5f52\uff08Symbolic Regression\uff09\u5728\u5386\u53f2\u4e0a\u5177\u6709\u91cd\u8981\u610f\u4e49\uff0c\u5176\u6839\u6e90\u53ef\u4ee5\u8ffd\u6eaf\u5230\u5f00\u666e\u52d2\u53d1\u73b0\u884c\u661f\u8fd0\u52a8\u5b9a\u5f8b…","_links":{"self":[{"href":"https:\/\/nullthought.net\/index.php?rest_route=\/wp\/v2\/posts\/4445","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=4445"}],"version-history":[{"count":2,"href":"https:\/\/nullthought.net\/index.php?rest_route=\/wp\/v2\/posts\/4445\/revisions"}],"predecessor-version":[{"id":4448,"href":"https:\/\/nullthought.net\/index.php?rest_route=\/wp\/v2\/posts\/4445\/revisions\/4448"}],"wp:attachment":[{"href":"https:\/\/nullthought.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4445"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/nullthought.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4445"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/nullthought.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4445"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}