{"id":43040,"date":"2023-06-09T16:56:18","date_gmt":"2023-06-09T08:56:18","guid":{"rendered":"https:\/\/swarma.org\/?p=43040"},"modified":"2023-06-09T16:56:18","modified_gmt":"2023-06-09T08:56:18","slug":"%e7%a7%91%e5%ad%a6%e5%90%af%e5%8f%91%e7%9a%84%e6%9c%ba%e5%99%a8%e5%ad%a6%e4%b9%a0%e7%90%86%e8%ae%ba%e4%b8%a8%e5%91%a8%e6%97%a5%e7%9b%b4%e6%92%ad%c2%b7-aiscience-%e8%af%bb%e4%b9%a6%e4%bc%9a","status":"publish","type":"post","link":"https:\/\/swarma.org\/?p=43040","title":{"rendered":"\u79d1\u5b66\u542f\u53d1\u7684\u673a\u5668\u5b66\u4e60\u7406\u8bba\u4e28\u5468\u65e5\u76f4\u64ad\u00b7 AI+Science \u8bfb\u4e66\u4f1a"},"content":{"rendered":"
\n
\n
\n
\n

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

\n
\n
\n
\n
\n
\n

<\/section>\n<\/section>\n
\n
\n

\u5bfc\u8bed<\/strong><\/p>\n<\/section>\n<\/section>\n

\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
\n
\n
\n

\u5728\u8fd9\u6b21\u8bfb\u4e66\u4f1a\u4e2d\uff0c\u8bb2\u8005\u4f1a\u7ed3\u5408\u4e00\u4e9b\u884c\u4e1a\u5927\u4f6c\u4eec\u7684\u89c2\u70b9\uff0c\u8ba8\u8bbaAI\u5230\u5e95\u9700\u8981\u4ec0\u4e48\u6837\u7684\u7406\u8bba\u3002\u4e3b\u6d41\u7684\u6709PAC learning theory\uff08Book: Foundations of machine learning\uff09\u548c\u57fa\u4e8e\u7edf\u8ba1\u7269\u7406\u7684\u5206\u6790(Book: Phase transitions in machine learning)\uff0c\u8bb2\u8005\u5c06\u7b80\u8981\u4ecb\u7ecd\u5e76\u8ba8\u8bba\u5b83\u4eec\u7684\u533a\u522b\u3002<\/span><\/strong><\/p>\n


<\/span><\/strong><\/p>\n

\u7406\u8bba\u6700\u7ec8\u662f\u7528\u6765\u670d\u52a1\u5b9e\u9a8c\u7684\uff0c\u7b2c\u4e00\u6b65\u662f\u5982\u4f55\u7528\u7406\u8bba\u7406\u89e3\u5df2\u6709\u7684\u5b9e\u9a8c\u73b0\u8c61(phenomenology), \u7b2c\u4e8c\u6b65\u662f\u7528\u7406\u8bba\u6307\u5bfc\u5b9e\u9a8c\u3002\u4e3a\u4e86\u505a\u5230\u7b2c\u4e00\u6b65\uff0c\u8bb2\u8005\u4f1a\u4ecb\u7ecd\u4e00\u4e9b\u5df2\u6709\u7684\u73b0\u8c61\uff0c\u4ee5\u53ca\u5982\u4f55\u6784\u5efa\u201c\u7269\u7406\u7406\u8bba\u201d\u6765\u89e3\u91ca\u8fd9\u4e9b\u73b0\u8c61\u3002\u8fd9\u4e9b\u73b0\u8c61\u5305\u62ec\uff1amemorization, phase transition, neural collapse, information bottleneck, representation learning\u7b49\u7b49\u3002\u8fd9\u4e9b\u4e0d\u540c\u7684\u73b0\u8c61\u5c31\u5982\u540c\u76f2\u4eba\u6478\u5230\u5927\u8c61\u7684\u4e0d\u540c\u4fa7\u9762\uff0c\u6211\u4eec\u5e0c\u671bAI\u7684\u201c\u5927\u7edf\u4e00\u7406\u8bba\u201d\u53ef\u4ee5\u7528\u4e00\u79cd\u81ea\u6d3d\u7684\u65b9\u5f0f\u523b\u753b\u6574\u5934\u5927\u8c61\u3002<\/span><\/strong><\/p>\n<\/section>\n

\n

<\/span><\/strong><\/strong><\/p>\n


<\/span><\/strong><\/p>\n

AI+Science<\/span><\/strong><\/a> \u662f\u8fd1\u5e74\u5174\u8d77\u7684\u5c06\u4eba\u5de5\u667a\u80fd\u548c\u79d1\u5b66\u76f8\u7ed3\u5408\u7684\u4e00\u79cd\u8d8b\u52bf\u3002\u96c6\u667a\u4ff1\u4e50\u90e8\u8054\u5408\u65af\u5766\u798f\u5927\u5b66\u8ba1\u7b97\u673a\u79d1\u5b66\u7cfb\u535a\u58eb\u540e\u7814\u7a76\u5458\u5434\u6cf0\u9716\u3001\u54c8\u4f5b\u91cf\u5b50\u8ba1\u5212\u7814\u7a76\u5458\u6248\u9e3f\u4e1a\u3001\u9ebb\u7701\u7406\u5de5\u5b66\u9662\u7269\u7406\u7cfb\u535a\u58eb\u751f\u5218\u5b50\u9e23\uff0c\u5171\u540c\u53d1\u8d77\u4ee5\u201cAI+Science\u201d\u4e3a\u4e3b\u9898\u7684\u8bfb\u4e66\u4f1a\uff0c\u4ece2023\u5e743\u670826\u65e5\u5f00\u59cb\uff0c\u6bcf\u5468\u65e5\u65e9\u4e0a 9:00-11:00 \u7ebf\u4e0a\u4e3e\u884c\uff0c\u6301\u7eed\u65f6\u95f4\u9884\u8ba110\u5468\u3002\u6b22\u8fce\u5bf9\u63a2\u7d22\u8fd9\u4e2a\u6fc0\u52a8\u4eba\u5fc3\u7684\u524d\u6cbf\u9886\u57df\u6709\u5174\u8da3\u7684\u670b\u53cb\u62a5\u540d\u53c2\u4e0e\u3002<\/span><\/strong><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

\n
\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
\n
<\/section>\n<\/section>\n

<\/section>\n
<\/section>\n


<\/p>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u5206\u4eab\u7b80\u4ecb<\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n

<\/section>\n
\u5b66\u4e60\u7406\u8bba\u662f\u4eba\u5de5\u667a\u80fd\u548c\u673a\u5668\u5b66\u4e60\u9886\u57df\u7684\u6838\u5fc3\u4e3b\u9898\uff0c\u5b83\u63a2\u8ba8\u4e86\u5982\u4f55\u4ece\u6570\u636e\u4e2d\u5b66\u4e60\u548c\u505a\u51fa\u9884\u6d4b\u7684\u57fa\u672c\u539f\u7406\u3002\u8fd9\u4e2a\u9886\u57df\u7684\u7814\u7a76\u95ee\u9898\u5305\u62ec\uff1a\u5982\u4f55\u5b9a\u4e49\u548c\u5ea6\u91cf\u5b66\u4e60\u7684\u6709\u6548\u6027\uff1f\u5982\u4f55\u8bbe\u8ba1\u6709\u6548\u7684\u5b66\u4e60\u7b97\u6cd5\uff1f\u4ee5\u53ca\u5982\u4f55\u7406\u89e3\u548c\u89e3\u91ca\u5b66\u4e60\u7b97\u6cd5\u7684\u884c\u4e3a\uff1f<\/span><\/section>\n
\u5728\u8fd9\u4e2a\u9886\u57df\u4e2d\uff0c\u6709\u4e24\u4e2a\u4e3b\u6d41\u7684\u7406\u8bba\u6846\u67b6\uff1aPAC\u5b66\u4e60\u7406\u8bba\u548c\u57fa\u4e8e\u7edf\u8ba1\u7269\u7406\u7684\u5206\u6790\u3002PAC\u5b66\u4e60\u7406\u8bba\uff0c\u5373\u6982\u7387\u8fd1\u4f3c\u6b63\u786e\uff08Probably Approximately Correct\uff09\u5b66\u4e60\u7406\u8bba\uff0c\u662f\u4e00\u79cd\u5f62\u5f0f\u5316\u7684\u5b66\u4e60\u7406\u8bba\uff0c\u5b83\u63d0\u4f9b\u4e86\u4e00\u79cd\u91cf\u5316\u5b66\u4e60\u7b97\u6cd5\u6027\u80fd\u7684\u65b9\u6cd5\u3002\u800c\u57fa\u4e8e\u7edf\u8ba1\u7269\u7406\u7684\u5206\u6790\u5219\u63d0\u4f9b\u4e86\u4e00\u79cd\u4ece\u5b8f\u89c2\u89d2\u5ea6\u7406\u89e3\u5b66\u4e60\u73b0\u8c61\u7684\u65b9\u6cd5\uff0c\u5b83\u5173\u6ce8\u7684\u662f\u5b66\u4e60\u7cfb\u7edf\u7684\u5168\u5c40\u6027\u8d28\u548c\u884c\u4e3a\u3002<\/span><\/section>\n

\u7136\u800c\uff0c\u8fd9\u4e24\u79cd\u7406\u8bba\u6846\u67b6\u90fd\u9762\u4e34\u7740\u6311\u6218\u3002\u4f8b\u5982\uff0cPAC\u5b66\u4e60\u7406\u8bba\u7684\u4e00\u4e9b\u5047\u8bbe\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\u53ef\u80fd\u4e0d\u6210\u7acb\uff0c\u800c\u57fa\u4e8e\u7edf\u8ba1\u7269\u7406\u7684\u5206\u6790\u5219\u9700\u8981\u5bf9\u7cfb\u7edf\u7684\u7ec6\u8282\u6709\u6df1\u5165\u7684\u7406\u89e3\u3002\u6b64\u5916\uff0c\u5982\u4f55\u5c06\u8fd9\u4e9b\u7406\u8bba\u5e94\u7528\u5230\u5b9e\u9645\u7684\u5b66\u4e60\u7cfb\u7edf\u4e2d\uff0c\u4ee5\u53ca\u5982\u4f55\u7528\u8fd9\u4e9b\u7406\u8bba\u6765\u89e3\u91ca\u548c\u9884\u6d4b\u5b9e\u9a8c\u73b0\u8c61\uff0c\u4e5f\u662f\u5f53\u524d\u7684\u7814\u7a76\u70ed\u70b9\u3002<\/span><\/p>\n


<\/p>\n


<\/p>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u5206\u4eab\u5927\u7eb2<\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n

<\/section>\n

1. \u5b66\u4e60\u7406\u8bba\u7684\u57fa\u672c\u6846\u67b6<\/span><\/p>\n

   1.1 PAC\u5b66\u4e60\u7406\u8bba\u7684\u4ecb\u7ecd<\/span><\/p>\n

   1.2 \u57fa\u4e8e\u7edf\u8ba1\u7269\u7406\u7684\u5206\u6790\u7684\u4ecb\u7ecd<\/span><\/p>\n

   1.3 \u8fd9\u4e24\u79cd\u7406\u8bba\u7684\u6bd4\u8f83\u548c\u533a\u522b<\/span><\/p>\n


<\/p>\n

2. \u7406\u8bba\u4e0e\u5b9e\u9a8c\u7684\u5173\u7cfb<\/span><\/p>\n

   2.1 \u5982\u4f55\u7528\u7406\u8bba\u7406\u89e3\u5df2\u6709\u7684\u5b9e\u9a8c\u73b0\u8c61<\/span><\/p>\n

   2.2 \u5982\u4f55\u7528\u7406\u8bba\u6307\u5bfc\u5b9e\u9a8c<\/span><\/p>\n


<\/p>\n

3. \u73b0\u8c61\u4e0e\u7406\u8bba\u7684\u5bf9\u5e94<\/span><\/p>\n

   3.1 \u8ba8\u8bba\u4e00\u4e9b\u5df2\u6709\u7684\u73b0\u8c61\uff0c\u5305\u62ec\uff1amemorization, phase transition, neural collapse, information bottleneck, representation learning\u7b49<\/span><\/p>\n

   3.2 \u5982\u4f55\u6784\u5efa\u201c\u7269\u7406\u7406\u8bba\u201d\u6765\u89e3\u91ca\u8fd9\u4e9b\u73b0\u8c61<\/span><\/p>\n


<\/p>\n

4. AI\u7684\u201c\u5927\u7edf\u4e00\u7406\u8bba\u201d<\/span><\/p>\n

   4.1 \u5bf9AI\u7684\u201c\u5927\u7edf\u4e00\u7406\u8bba\u201d\u7684\u63a2\u7d22<\/span><\/p>\n

   4.2 \u5982\u4f55\u7528\u4e00\u79cd\u81ea\u6d3d\u7684\u65b9\u5f0f\u523b\u753b\u6574\u4e2a\u5b66\u4e60\u7cfb\u7edf<\/span><\/p>\n


<\/span><\/section>\n

<\/span><\/section>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u6838\u5fc3\u6982\u5ff5<\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n

<\/section>\n
1. PAC\u5b66\u4e60\u7406\u8bba\uff1aPAC\uff08Probably Approximately Correct\uff09\u5b66\u4e60\u7406\u8bba\u662f\u7531Leslie Valiant\u63d0\u51fa\u7684\uff0c\u5b83\u662f\u4e00\u79cd\u5f62\u5f0f\u5316\u7684\u5b66\u4e60\u7406\u8bba\uff0c\u63d0\u4f9b\u4e86\u4e00\u79cd\u91cf\u5316\u5b66\u4e60\u7b97\u6cd5\u6027\u80fd\u7684\u65b9\u6cd5\u3002\u7b80\u5355\u6765\u8bf4\uff0c\u4e00\u4e2aPAC\u5b66\u4e60\u7b97\u6cd5\u80fd\u591f\u5728\u591a\u9879\u5f0f\u65f6\u95f4\u5185\u627e\u5230\u4e00\u4e2a\u8fd1\u4f3c\u6b63\u786e\u7684\u5047\u8bbe\uff0c\u8fd9\u4e2a\u5047\u8bbe\u5728\u5927\u591a\u6570\u60c5\u51b5\u4e0b\u90fd\u662f\u6b63\u786e\u7684\u3002<\/span><\/section>\n

<\/section>\n
2. \u57fa\u4e8e\u7edf\u8ba1\u7269\u7406\u7684\u5206\u6790\uff1a\u8fd9\u662f\u4e00\u79cd\u4ece\u5b8f\u89c2\u89d2\u5ea6\u7406\u89e3\u5b66\u4e60\u73b0\u8c61\u7684\u65b9\u6cd5\uff0c\u5b83\u5173\u6ce8\u7684\u662f\u5b66\u4e60\u7cfb\u7edf\u7684\u5168\u5c40\u6027\u8d28\u548c\u884c\u4e3a\u3002\u8fd9\u79cd\u65b9\u6cd5\u901a\u5e38\u9700\u8981\u5bf9\u7cfb\u7edf\u7684\u7ec6\u8282\u6709\u6df1\u5165\u7684\u7406\u89e3\u3002\u63a8\u8350\uff1a\u5730\u7403\u7cfb\u7edf\u79d1\u5b66\u8bfb\u4e66\u4f1a\u7b2c\u4e8c\u671f\u300a\u5730\u7403\u7cfb\u7edf\u79d1\u5b66\u4e2d\u7684\u7edf\u8ba1\u7269\u7406\u7406\u8bba<\/a>\u300b\uff0c\u4ecb\u7ecd\u4e86\u6709\u5173\u7edf\u8ba1\u7269\u7406\u5b66\u7684\u57fa\u672c\u6982\u5ff5\u548c\u7406\u8bba\uff0c\u4ee5\u53ca\u5982\u4f55\u5c06\u5176\u5e94\u7528\u4e8e\u5730\u7403\u590d\u6742\u7cfb\u7edf\u3002<\/span><\/section>\n

<\/section>\n
3. Memorization\uff1a\u5728\u673a\u5668\u5b66\u4e60\u4e2d\uff0c\u8bb0\u5fc6\u5316\u662f\u6307\u6a21\u578b\u5b66\u4e60\u5230\u8bad\u7ec3\u6570\u636e\u7684\u7279\u5b9a\u7ec6\u8282\uff0c\u800c\u4e0d\u4ec5\u4ec5\u662f\u6982\u62ec\u7684\u6a21\u5f0f\u3002\u8fd9\u53ef\u80fd\u4f1a\u5bfc\u81f4\u8fc7\u62df\u5408\uff0c\u5373\u6a21\u578b\u5728\u8bad\u7ec3\u6570\u636e\u4e0a\u8868\u73b0\u826f\u597d\uff0c\u4f46\u5728\u65b0\u7684\u3001\u672a\u89c1\u8fc7\u7684\u6570\u636e\u4e0a\u8868\u73b0\u4e0d\u4f73\u3002<\/span><\/section>\n

<\/section>\n
4. Phase Transition\uff1a\u5728\u7edf\u8ba1\u7269\u7406\u4e2d\uff0c\u76f8\u53d8\u662f\u6307\u7cfb\u7edf\u4ece\u4e00\u79cd\u72b6\u6001\u7a81\u7136\u8f6c\u53d8\u4e3a\u53e6\u4e00\u79cd\u72b6\u6001\u3002\u5728\u673a\u5668\u5b66\u4e60\u4e2d\uff0c\u76f8\u53d8\u53ef\u80fd\u6307\u7684\u662f\u5b66\u4e60\u8fc7\u7a0b\u4e2d\u7684\u67d0\u79cd\u7a81\u53d8\uff0c\u4f8b\u5982\u6a21\u578b\u7684\u6027\u80fd\u7a81\u7136\u63d0\u9ad8\u6216\u964d\u4f4e\u3002\u63a8\u8350\uff1a\u5317\u4eac\u5e08\u8303\u5927\u5b66\u7cfb\u7edf\u79d1\u5b66\u5b66\u9662\u9662\u957f\u9648\u6653\u677e\u8001\u5e08\u5173\u4e8e\u300a\u590d\u6742\u6027\u4e0e\u4e34\u754c\u73b0\u8c61\u300b\u7684\u8bfe\u7a0b\uff08\u5730\u5740\uff1ahttps:\/\/campus.swarma.org\/course\/1131\uff09\uff0c\u91cc\u9762\u8be6\u7ec6\u5730\u4ecb\u7ecd\u4e86\u76f8\u53d8\u7b49\u6838\u5fc3\u6982\u5ff5\u3002<\/span><\/section>\n

<\/section>\n
5. Neural Collapse\uff1a\u795e\u7ecf\u584c\u7f29\u662f\u6307\u5728\u6df1\u5ea6\u5b66\u4e60\u8bad\u7ec3\u8fc7\u7a0b\u4e2d\uff0c\u76f8\u540c\u6807\u7b7e\u6837\u672c\u7684\u8868\u793a\u53d1\u751f\u584c\u7f29\uff0c\u4e0d\u540c\u6807\u7b7e\u6837\u672c\u7684\u4e2d\u5fc3\u6784\u6210\u4e00\u4e2a\u8d85\u9525\u4f53\u3002https:\/\/www.pnas.org\/doi\/10.1073\/pnas.2015509117<\/span><\/section>\n

<\/section>\n
6. Information Bottleneck\uff1a\u4fe1\u606f\u74f6\u9888\u662f\u4e00\u79cd\u7406\u8bba\u6846\u67b6\uff0c\u7528\u4e8e\u7406\u89e3\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\u5982\u4f55\u4ece\u8f93\u5165\u6570\u636e\u4e2d\u63d0\u53d6\u6709\u7528\u7684\u4fe1\u606f\u3002\u5b83\u7684\u6838\u5fc3\u601d\u60f3\u662f\uff0c\u6a21\u578b\u5e94\u8be5\u5c3d\u53ef\u80fd\u5730\u538b\u7f29\u8f93\u5165\u6570\u636e\uff0c\u540c\u65f6\u4fdd\u7559\u4e0e\u76ee\u6807\u4efb\u52a1\u76f8\u5173\u7684\u4fe1\u606f\u3002\u63a8\u8350\uff1a\u56e0\u679c\u6d8c\u73b0\u8bfb\u4e66\u4f1a\u7b2c\u4e8c\u5b63<\/a>\u72b9\u4ed6\u5927\u5b66\u7684\u5728\u8bfb\u535a\u58eb\u751f\u65b9\u69af\u6977\u7684\u5206\u4eab\uff0c\u5176\u4e2d\u91cd\u70b9\u4ecb\u7ecd\u4e86\u4fe1\u606f\u74f6\u9888\u7406\u8bba\u4e0e\u56e0\u679c\u5b8f\u89c2\u53d8\u91cf\u7f16\u7801\u3002<\/span><\/section>\n

<\/section>\n
7. Representation Learning\uff1a\u8868\u793a\u5b66\u4e60\u662f\u673a\u5668\u5b66\u4e60\u7684\u4e00\u4e2a\u91cd\u8981\u4efb\u52a1\uff0c\u5b83\u7684\u76ee\u6807\u662f\u627e\u5230\u4e00\u79cd\u80fd\u591f\u6355\u6349\u5230\u6570\u636e\u672c\u8d28\u7ed3\u6784\u548c\u7279\u6027\u7684\u6570\u636e\u8868\u793a\u65b9\u6cd5\u3002\u8fd9\u79cd\u8868\u793a\u65b9\u6cd5\u53ef\u4ee5\u4f7f\u5f97\u540e\u7eed\u7684\u5b66\u4e60\u4efb\u52a1\u66f4\u52a0\u5bb9\u6613\u3002\u56e0\u679c\u8868\u5f81\u5b66\u4e60\u5219\u662f\u5728\u8868\u5f81\u5b66\u4e60\u7684\u57fa\u7840\u4e0a\uff0c\u8fdb\u4e00\u6b65\u5f15\u5165\u4e86\u56e0\u679c\u5173\u7cfb\u7684\u8003\u8651\u3002\u5b83\u7684\u76ee\u6807\u4e0d\u4ec5\u662f\u627e\u5230\u4e00\u79cd\u6709\u6548\u7684\u6570\u636e\u8868\u793a\uff0c\u800c\u4e14\u8fd9\u79cd\u8868\u793a\u8fd8\u9700\u8981\u80fd\u591f\u63ed\u793a\u6570\u636e\u4e2d\u7684\u56e0\u679c\u5173\u7cfb\u3002\u8fd9\u6837\u7684\u8868\u793a\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u7406\u89e3\u6570\u636e\u751f\u6210\u7684\u673a\u5236\uff0c\u9884\u6d4b\u5e72\u9884\u6216\u53d8\u5316\u6761\u4ef6\u4e0b\u7684\u7ed3\u679c\uff0c\u63a8\u8350\u96c6\u667a\u4ff1\u4e50\u90e8\u7684\u300c\u56e0\u679c\u8868\u5f81\u5b66\u4e60\u300d\u8bfb\u4e66\u4f1a<\/a>\uff0c\u7cfb\u7edf\u6027\u7684\u63a2\u8ba8\u4e86\u56e0\u679c\u8868\u5f81\u5b66\u4e60\u7684\u6574\u4f53\u6846\u67b6\u3002<\/span><\/section>\n

<\/section>\n


<\/p>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u4e3b\u8bb2\u4eba\u4ecb\u7ecd<\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n
<\/p>\n
<\/span>
<\/strong><\/section>\n

<\/p>\n

\u5218\u5b50\u9e23<\/span><\/strong>\uff0c\u76ee\u524d\u662f\u9ebb\u7701\u7406\u5de5\u5b66\u9662\uff08MIT\uff09\u7269\u7406\u7cfb\u535a\u58eb\u751f\uff0c\u5bfc\u5e08\u662fMax Tegmark\u3002\u6b64\u524d2020\u5e74\u4ed6\u4ece\u5317\u4eac\u5927\u5b66\u83b7\u5f97\u7269\u7406\u5b66\u58eb\u5b66\u4f4d\u3002\u4ed6\u7684\u7814\u7a76\u5174\u8da3\u5728AI\u548c\u7269\u7406\u7684\u4ea4\u53c9\uff1a\u4e00\u65b9\u9762AI for Physics\uff0c\u5229\u7528AI\u5de5\u5177\u81ea\u52a8\u5316\u7269\u7406\u89c4\u5f8b\u548c\u6982\u5ff5\u7684\u53d1\u73b0\uff1b\u53e6\u4e00\u65b9\u9762Physics for AI\uff0c\u5229\u7528\u7269\u7406\u542f\u53d1\u6784\u5efaAI\u7406\u8bba\u548c\u66f4\u5177\u53ef\u89e3\u91ca\u6027\u7684\u6a21\u578b\u3002<\/span><\/section>\n

<\/section>\n

<\/section>\n

<\/span><\/section>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u76f4\u64ad\u4fe1\u606f<\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n

<\/section>\n

\u76f4\u64ad\u65f6\u95f4\uff1a<\/span><\/strong><\/h3>\n

2023\u5e746\u670811\u65e5\uff08\u5468\u65e5\uff09  20:00-22:00<\/span><\/span><\/h3>\n

<\/h3>\n

<\/section>\n
\u53c2\u4e0e\u65b9\u5f0f\uff1a<\/span><\/strong>\u4ec5B\u7ad9\u76f4\u64ad<\/strong><\/section>\n
<\/span><\/section>\n
\u626b\u7801\u53c2\u4e0e\u8bfb\u4e66\u4f1a\uff0c\u52a0\u5165\u7fa4\u804a\u83b7\u53d6\u672c\u7cfb\u5217\u8bfb\u4e66\u4f1a\u7684\u89c6\u9891\u56de\u653e\u6743\u9650\u3001\u8d44\u6599\u6743\u9650\uff0c\u4e0e\u793e\u533a\u7684\u4e00\u7ebf\u79d1\u7814\u5de5\u4f5c\u8005\u548c\u4f01\u4e1a\u5b9e\u8df5\u8005\u6c9f\u901a\u4ea4\u6d41\u3002<\/span><\/section>\n

<\/section>\n

<\/section>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u63a8\u8350\u5b66\u4e60\u8d44\u6e90<\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n
<\/p>\n
\n


<\/p>\n

1. \u300aFoundations of Machine Learning\u300b\uff1a\u8fd9\u672c\u4e66\u8be6\u7ec6\u4ecb\u7ecd\u4e86PAC\u5b66\u4e60\u7406\u8bba\u548c\u5176\u4ed6\u673a\u5668\u5b66\u4e60\u7684\u57fa\u672c\u7406\u8bba\u3002<\/span><\/p>\n


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

<\/p>\n


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

2. \u300aPhase Transitions in Machine Learning\u300b\uff1a\u8fd9\u672c\u4e66\u4ece\u7edf\u8ba1\u7269\u7406\u7684\u89d2\u5ea6\u5206\u6790\u4e86\u673a\u5668\u5b66\u4e60\u4e2d\u7684\u4e00\u4e9b\u73b0\u8c61\uff0c\u5305\u62ec\u76f8\u53d8\u3002<\/span><\/p>\n


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

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


<\/section>\n
3. <\/span>\u673a\u5668\u5b66\u4e60\u7684 Learning theory \u5b66\u4e60\u7406\u8bba\u7efc\u8ff0<\/span><\/a><\/section>\n

<\/span><\/section>\n


<\/section>\n
\n
\n
\n
\n

AI+Science \u8bfb\u4e66\u4f1a\u542f\u52a8<\/strong><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

\n


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

AI+Science \u662f\u8fd1\u5e74\u5174\u8d77\u7684\u5c06\u4eba\u5de5\u667a\u80fd\u548c\u79d1\u5b66\u76f8\u7ed3\u5408\u7684\u4e00\u79cd\u8d8b\u52bf\u3002\u4e00\u65b9\u9762\u662f AI for Science\uff0c\u673a\u5668\u5b66\u4e60\u548c\u5176\u4ed6 AI \u6280\u672f\u53ef\u4ee5\u7528\u6765\u89e3\u51b3\u79d1\u5b66\u7814\u7a76\u4e2d\u7684\u95ee\u9898\uff0c\u4ece\u9884\u6d4b\u5929\u6c14\u548c\u86cb\u767d\u8d28\u7ed3\u6784\uff0c\u5230\u6a21\u62df\u661f\u7cfb\u78b0\u649e\u3001\u8bbe\u8ba1\u4f18\u5316\u6838\u805a\u53d8\u53cd\u5e94\u5806\uff0c\u751a\u81f3\u50cf\u79d1\u5b66\u5bb6\u4e00\u6837\u8fdb\u884c\u79d1\u5b66\u53d1\u73b0\uff0c\u88ab\u79f0\u4e3a\u79d1\u5b66\u53d1\u73b0\u7684\u201c\u7b2c\u4e94\u8303\u5f0f\u201d\u3002\u53e6\u4e00\u65b9\u9762\u662f Science for AI\uff0c\u79d1\u5b66\u5c24\u5176\u662f\u7269\u7406\u5b66\u4e2d\u7684\u89c4\u5f8b\u548c\u601d\u60f3\u542f\u53d1\u673a\u5668\u5b66\u4e60\u7406\u8bba\uff0c\u4e3a\u4eba\u5de5\u667a\u80fd\u7684\u53d1\u5c55\u63d0\u4f9b\u5168\u65b0\u7684\u89c6\u89d2\u548c\u65b9\u6cd5\u3002<\/span><\/section>\n

<\/section>\n
\u96c6\u667a\u4ff1\u4e50\u90e8\u8054\u5408\u65af\u5766\u798f\u5927\u5b66\u8ba1\u7b97\u673a\u79d1\u5b66\u7cfb\u535a\u58eb\u540e\u7814\u7a76\u5458\u5434\u6cf0\u9716\uff08Jure Leskovec \u6559\u6388\u6307\u5bfc\uff09\u3001\u54c8\u4f5b\u91cf\u5b50\u8ba1\u5212\u7814\u7a76\u5458\u6248\u9e3f\u4e1a\u3001\u9ebb\u7701\u7406\u5de5\u5b66\u9662\u7269\u7406\u7cfb\u535a\u58eb\u751f\u5218\u5b50\u9e23\uff08Max Tegmark \u6559\u6388\u6307\u5bfc\uff09\uff0c\u5171\u540c\u53d1\u8d77\u4ee5\u201cAI+Science<\/a>\u201d\u4e3a\u4e3b\u9898\u7684\u8bfb\u4e66\u4f1a\uff0c\u63a2\u8ba8\u8be5\u9886\u57df\u7684\u91cd\u8981\u95ee\u9898\uff0c\u5171\u5b66\u5171\u7814\u76f8\u5173\u6587\u732e\u3002\u8bfb\u4e66\u4f1a\u4ece2023\u5e743\u670826\u65e5\u5f00\u59cb\uff0c\u6bcf\u5468\u65e5\u65e9\u4e0a 10:00-12:00 \u7ebf\u4e0a\u4e3e\u884c\uff0c\u6301\u7eed\u65f6\u95f4\u9884\u8ba110\u5468\u3002\u6b22\u8fce\u5bf9\u63a2\u7d22\u8fd9\u4e2a\u6fc0\u52a8\u4eba\u5fc3\u7684\u524d\u6cbf\u9886\u57df\u6709\u5174\u8da3\u7684\u670b\u53cb\u62a5\u540d\u53c2\u4e0e\u3002<\/span><\/section>\n

<\/section>\n
<\/span><\/span><\/a><\/section>\n

<\/section>\n
\u8be6\u60c5\u8bf7\u89c1\uff1a<\/span><\/section>\n
\u4eba\u5de5\u667a\u80fd\u548c\u79d1\u5b66\u53d1\u73b0\u76f8\u4e92\u8d4b\u80fd\u7684\u65b0\u8303\u5f0f\uff1aAI+Science \u8bfb\u4e66\u4f1a\u542f\u52a8<\/a><\/section>\n

<\/section>\n
<\/span><\/section>\n


<\/p>\n

\n
\n
\n
\n

\u96c6\u667a\u5b66\u56ed\u6700\u65b0AI\u8bfe\u7a0b\uff0c<\/strong><\/p>\n

\u5f20\u6c5f\u6559\u6388\u4eb2\u6388\uff1a<\/strong>\u7b2c\u4e09\u4ee3\u4eba\u5de5\u667a\u80fd\u6280\u672f\u57fa\u7840<\/strong><\/p>\n

\u2014\u2014\u4ece\u53ef\u5fae\u5206\u7f16\u7a0b\u5230\u56e0\u679c\u63a8\u7406<\/strong><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

\n
<\/span><\/section>\n<\/section>\n

<\/section>\n
<\/span><\/section>\n

\u81ea1956\u5e74\u201c\u4eba\u5de5\u667a\u80fd\u201d\u8bde\u751f\u4e8e\u8fbe\u7279\u8305\u65af\u4f1a\u8bae\u4ee5\u6765\uff0c\u5df2\u7ecf\u7ecf\u5386\u4e86\u4ece\u65e9\u671f\u7684\u4ee5\u7b26\u53f7\u63a8\u7406\u4e3a\u4e3b\u4f53\u7684\u7b2c\u4e00\u4ee3\u4eba\u5de5\u667a\u80fd\uff0c\u548c\u4ee5\u6df1\u5ea6\u795e\u7ecf\u7f51\u7edc\u3001\u673a\u5668\u5b66\u4e60\u4e3a\u4e3b\u4f53\u7684\u7b2c\u4e8c\u4ee3\u4eba\u5de5\u667a\u80fd\u3002ChatGPT\u7684\u6a2a\u7a7a\u51fa\u4e16\u3001\u751f\u6210\u5f0fAI\u7684\u666e\u53ca\u3001AI for Science\u7b49\u65b0\u9886\u57df\u7684\u7a81\u7834\uff0c\u6807\u5fd7\u7740\u7b2c\u4e09\u4ee3\u4eba\u5de5\u667a\u80fd\u7684\u547c\u4e4b\u6b32\u51fa\u3002\u53ef\u5fae\u5206\u7f16\u7a0b\u3001\u795e\u7ecf\u5fae\u5206\u65b9\u7a0b\u3001\u81ea\u76d1\u7763\u5b66\u4e60\u3001\u751f\u6210\u5f0f\u6a21\u578b\u3001Transformer\u3001\u57fa\u4e8e\u56fe\u7f51\u7edc\u7684\u5b66\u4e60\u4e0e\u63a8\u7406\u3001\u56e0\u679c\u8868\u5f81\u4e0e\u56e0\u679c\u63a8\u65ad\uff0c\u57fa\u4e8e\u4e16\u754c\u6a21\u578b\u7684\u5f3a\u5316\u5b66\u4e60\u2026\u2026\uff0c\u6240\u6709\u8fd9\u4e9b\u8131\u80ce\u4e8e\u524d\u4e24\u4ee3\u4eba\u5de5\u667a\u80fd\u7684\u6280\u672f\u8981\u7d20\u5f88\u6709\u53ef\u80fd\u5c06\u6784\u6210\u7b2c\u4e09\u4ee3\u4eba\u5de5\u667a\u80fd\u7684\u7406\u8bba\u4e0e\u6280\u672f\u7684\u57fa\u7840\u3002<\/span><\/p>\n


<\/section>\n
\u672c\u8bfe\u7a0b\u8bd5\u56fe\u7cfb\u7edf\u68b3\u7406\u4ece\u673a\u5668\u5b66\u4e60\u5230\u5927\u8bed\u8a00\u6a21\u578b\uff0c\u4ece\u56fe\u795e\u7ecf\u7f51\u7edc\u5230\u56e0\u679c\u63a8\u7406\u7b49\u4e00\u7cfb\u5217\u53ef\u80fd\u6210\u4e3a\u7b2c\u4e09\u4ee3\u4eba\u5de5\u667a\u80fd\u57fa\u7840\u7684\u6280\u672f\u8981\u7d20\uff0c\u4e3a\u7814\u7a76\u8005\u6216\u5b66\u751f\u5728\u751f\u6210\u5f0fAI\u3001\u5927\u6a21\u578b\u3001AI for Science\u7b49\u76f8\u5173\u9886\u57df\u7684\u5b66\u4e60\u548c\u7814\u7a76\u5de5\u4f5c\u5960\u5b9a\u57fa\u7840\u3002<\/span><\/section>\n

<\/section>\n
<\/span><\/section>\n
<\/section>\n
https:\/\/campus.swarma.org\/course\/5084?from=wechat<\/span><\/section>\n

<\/section>\n

<\/section>\n
\n
\n
\n
\n

\u56fe\u795e\u7ecf\u7f51\u7edc\u4e0e\u7ec4\u5408\u4f18\u5316\u8bfb\u4e66\u4f1a\u542f\u52a8<\/strong><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

\n


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

\u73b0\u5b9e\u4e16\u754c\u4e2d\u5927\u91cf\u95ee\u9898\u7684\u89e3\u51b3\u4f9d\u8d56\u4e8e\u7b97\u6cd5\u7684\u8bbe\u8ba1\u4e0e\u6c42\u89e3\u3002\u4f20\u7edf\u7b97\u6cd5\u7531\u4eba\u7c7b\u4e13\u5bb6\u8bbe\u8ba1\uff0c\u800c\u968f\u7740\u4eba\u5de5\u667a\u80fd\u6280\u672f\u4e0d\u65ad\u53d1\u5c55\uff0c\u7b97\u6cd5\u81ea\u52a8\u5b66\u4e60\u7b97\u6cd5\u7684\u6848\u4f8b\u65e5\u76ca\u589e\u591a\uff0c\u5982\u4ee5\u795e\u7ecf\u7f51\u7edc\u4e3a\u4ee3\u8868\u7684\u7684\u4eba\u5de5\u667a\u80fd\u7b97\u6cd5\uff0c\u8fd9\u662f\u7b97\u6cd5\u795e\u7ecf\u5316\u6c42\u89e3\u7684\u7f18\u7531\u3002\u5728\u7b97\u6cd5\u795e\u7ecf\u5316\u6c42\u89e3\u65b9\u5411\u4e0a\uff0c\u56fe\u795e\u7ecf\u7f51\u7edc\u662f\u4e00\u4e2a\u5f3a\u6709\u529b\u7684\u5de5\u5177\uff0c\u80fd\u591f\u5145\u5206\u5229\u7528\u56fe\u7ed3\u6784\u7684\u7279\u6027\uff0c\u5b9e\u73b0\u5bf9\u9ad8\u590d\u6742\u5ea6\u7b97\u6cd5\u7684\u9ad8\u6548\u8fd1\u4f3c\u6c42\u89e3\u3002\u57fa\u4e8e\u56fe\u795e\u7ecf\u7f51\u7edc\u7684\u590d\u6742\u7cfb\u7edf\u4f18\u5316\u4e0e\u63a7\u5236\u5c06\u4f1a\u662f\u5927\u6a21\u578b\u70ed\u6f6e\u4e4b\u540e\u65b0\u7684\u672a\u6765\u65b9\u5411\u3002<\/span><\/section>\n

<\/span><\/section>\n
\u4e3a\u4e86\u63a2\u8ba8\u56fe\u795e\u7ecf\u7f51\u7edc\u5728\u7b97\u6cd5\u795e\u7ecf\u5316\u6c42\u89e3\u7684\u53d1\u5c55\u4e0e\u73b0\u5b9e\u5e94\u7528\uff0c\u96c6\u667a\u4ff1\u4e50\u90e8\u8054\u5408\u56fd\u9632\u79d1\u6280\u5927\u5b66\u7cfb\u7edf\u5de5\u7a0b\u5b66\u9662\u526f\u6559\u6388\u8303\u957f\u4fca\u3001\u4e2d\u56fd\u4eba\u6c11\u5927\u5b66\u9ad8\u74f4\u4eba\u5de5\u667a\u80fd\u5b66\u9662\u52a9\u7406\u6559\u6388\u9ec4\u6587\u70b3\uff0c\u5171\u540c\u53d1\u8d77\u300c\u56fe\u795e\u7ecf\u7f51\u7edc\u4e0e\u7ec4\u5408\u4f18\u5316\u300d\u8bfb\u4e66\u4f1a\u3002\u8bfb\u4e66\u4f1a\u5c06\u805a\u7126\u4e8e\u56fe\u795e\u7ecf\u7f51\u7edc\u4e0e\u7b97\u6cd5\u795e\u7ecf\u5316\u6c42\u89e3\u7684\u76f8\u5173\u9886\u57df\uff0c\u5305\u62ec\u795e\u7ecf\u7b97\u6cd5\u63a8\u7406\u3001\u7ec4\u5408\u4f18\u5316\u95ee\u9898\u6c42\u89e3\u3001\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\uff0c\u4ee5\u53ca\u7b97\u6cd5\u795e\u7ecf\u5316\u6c42\u89e3\u5728 AI for Science \u4e2d\u7684\u5e94\u7528\u7b49\u65b9\u9762\uff0c\u5e0c\u671b\u4e3a\u53c2\u4e0e\u8005\u63d0\u4f9b\u4e00\u4e2a\u5b66\u672f\u4ea4\u6d41\u5e73\u53f0\uff0c\u6fc0\u53d1\u53c2\u4e0e\u8005\u7684\u5b66\u672f\u5174\u8da3\uff0c\u8fdb\u4e00\u6b65\u63a8\u52a8\u76f8\u5173\u9886\u57df\u7684\u7814\u7a76\u548c\u5e94\u7528\u53d1\u5c55\u3002\u8bfb\u4e66\u4f1a\u4ece2023\u5e746\u670814\u65e5\u5f00\u59cb\uff0c\u6bcf\u5468\u4e09\u665a 19:00-21:00 \u4e3e\u884c\uff0c\u6301\u7eed\u65f6\u95f4\u9884\u8ba18\u5468\u3002\u6b22\u8fce\u611f\u5174\u8da3\u7684\u670b\u53cb\u62a5\u540d\u53c2\u4e0e\uff01<\/span><\/section>\n

<\/span><\/section>\n
<\/span><\/a><\/section>\n
\u8be6\u60c5\u8bf7\u89c1\uff1a<\/span><\/section>\n
\u52a0\u901f\u7ecf\u5178\u7b97\u6cd5\u6548\u7387\uff0c\u7a81\u7834\u73b0\u5b9e\u6280\u672f\u74f6\u9888\uff1a\u56fe\u795e\u7ecf\u7f51\u7edc\u4e0e\u7ec4\u5408\u4f18\u5316\u8bfb\u4e66\u4f1a\u542f\u52a8<\/a><\/span>
<\/span><\/section>\n


<\/p>\n


<\/section>\n

\u70b9\u51fb\u201c\u9605\u8bfb\u539f\u6587\u201d\uff0c\u62a5\u540d\u8bfb\u4e66\u4f1a<\/span><\/p>\n

<\/mp-style-type><\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

\u5bfc\u8bed \u5728\u8fd9\u6b21\u8bfb\u4e66\u4f1a\u4e2d\uff0c\u8bb2\u8005\u4f1a\u7ed3\u5408\u4e00\u4e9b\u884c\u4e1a\u5927\u4f6c\u4eec\u7684\u89c2\u70b9\uff0c\u8ba8\u8bbaAI\u5230\u5e95\u9700\u8981\u4ec0\u4e48\u6837\u7684\u7406\u8bba\u3002\u4e3b\u6d41\u7684\u6709PAC learning theory\uff08Book: Foundations of machine learning\uff09\u548c\u57fa\u4e8e\u7edf\u8ba1\u7269\u7406\u7684\u5206\u6790(Book: Phase transitions in machine …<\/p>\n","protected":false},"author":0,"featured_media":43033,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"special":[],"_links":{"self":[{"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/posts\/43040"}],"collection":[{"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=43040"}],"version-history":[{"count":0,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/posts\/43040\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/media\/43033"}],"wp:attachment":[{"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=43040"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=43040"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=43040"},{"taxonomy":"special","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fspecial&post=43040"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}