{"id":22742,"date":"2020-12-17T17:30:16","date_gmt":"2020-12-17T09:30:16","guid":{"rendered":"https:\/\/swarma.org\/?p=22742"},"modified":"2020-12-17T17:30:16","modified_gmt":"2020-12-17T09:30:16","slug":"%e5%91%a8%e6%97%a5%e7%9b%b4%e6%92%ad%ef%bc%9a%e5%9b%a0%e6%9e%9c%e7%a7%91%e5%ad%a6%e5%9c%a8%e5%b7%a5%e4%b8%9a%e7%95%8c%e7%9a%84%e5%ba%94%e7%94%a8-%e5%9b%a0%e6%9e%9c%e7%a7%91%e5%ad%a6%e4%b8%8ecausal-a","status":"publish","type":"post","link":"https:\/\/swarma.org\/?p=22742","title":{"rendered":"\u5468\u65e5\u76f4\u64ad\uff1a\u56e0\u679c\u79d1\u5b66\u5728\u5de5\u4e1a\u754c\u7684\u5e94\u7528 | \u56e0\u679c\u79d1\u5b66\u4e0eCausal AI\u8bfb\u4e66\u4f1a"},"content":{"rendered":"
\n
<\/span><\/section>\n
<\/section>\n

<\/section>\n
<\/p>\n
\u672c\u5468\u65e5\u4e0a\u53489\uff1a<\/span>00\uff0c\u201c\u56e0\u679c\u79d1\u5b66\u4e0eCausal AI\u201d\u8bfb\u4e66\u4f1a\u5c06\u8fdb\u884c\u7b2c\u5341\u4e09\u671f\u7684\u7ebf\u4e0a\u8bba\u6587\u5206\u4eab\uff0c\u4e3b\u9898\u662f\u201c\u56e0\u679c\u79d1\u5b66\u5728\u5de5\u4e1a\u754c\u7684\u524d\u6cbf\u5e94\u7528\u201d\uff0c\u5c06\u7531Etsy\u7684\u6570\u636e\u79d1\u5b66\u5bb6XuanYin\u548c\u5357\u6d0b\u7406\u5de5\u5927\u5b66\u535a\u58eb\u5728\u8bfb\uff0c\u540c\u65f6\u4e5f\u5728\u8fbe\u6469\u9662\u5de5\u4f5c\u7684\u6c64\u632f\u534e\u5206\u4eab\u56e0\u679c\u79d1\u5b66\u5728\u5de5\u4e1a\u754c\u7684\u4e00\u4e9b\u524d\u6cbf\u5e94\u7528\uff0c\u7684\u672c\u6b21\u5185\u5bb9\u5c06\u5728\u96c6\u667a\u4ff1\u4e50\u90e8B\u7ad9\u76f4\u64ad\uff0c\u6b22\u8fce\u5927\u5bb6\u626b\u7801\u62a5\u540d\uff0c\u83b7\u53d6\u63d0\u9192\u3002<\/span><\/section>\n


<\/p>\n

 <\/span><\/p>\n

\n
\n
\n
\n

<\/section>\n

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

Solving Interference in Marketplace Experiments<\/span><\/strong><\/span><\/strong><\/strong><\/span><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

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

<\/section>\n<\/h2>\n

Xuan Yin\uff0cData Scientist in Etsy\uff0c\u7814\u7a76\u65b9\u5411\u4e3a\u56e0\u679c\u63a8\u7406\u3002<\/span><\/p>\n


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

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


<\/p>\n

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

\u8bb8\u591a\u7684\u7535\u5b50\u5546\u52a1\u516c\u53f8\u7684\u4e3b\u8425\u4e1a\u52a1\u662f\u7ebf\u4e0a\u5e02\u573a\u3002\u8fd9\u5305\u62ec\u7ebf\u4e0a\u6279\u53d1\u5e02\u573a\uff0c\u4f8b\u5982\u963f\u91cc\u5df4\u5df4\uff1b\u7ebf\u4e0a\u96f6\u552e\u5e02\u573a\uff0c\u4f8b\u5982Amazon\uff0ceBay\uff0cEtsy\uff1b\u5171\u4eab\u7ecf\u6d4e\uff0c\u4f8b\u5982Uber\uff0cLyft\uff0cAirbnb\u3002\u8fd9\u4e9b\u7535\u5b50\u5546\u52a1\u516c\u53f8\u5982\u540c\u5176\u4ed6\u7684\u4e92\u8054\u7f51\u516c\u53f8\u4e00\u6837\uff0c\u4ee5\u968f\u673a\u5b9e\u9a8c\u6765\u4f30\u8ba1\u68c0\u9a8cAverage Treatment Effect<\/span>\uff08online A\/B tests\uff09<\/span>\uff0c\u4ece\u800c\u505a\u51fa\u4e1a\u52a1\u51b3\u7b56\uff0c\u4f8b\u5982\uff1a\u662f\u5426\u5e94\u8be5\u91c7\u7528\u65b0\u7684\u7b97\u6cd5\u6765\u652f\u6301\u4ea7\u54c1\uff0c\u65b0\u7684\u4ea7\u54c1\u5e26\u6765\u4e86\u591a\u5c11\u5229\u76ca\uff0c\u7b49\u7b49\u3002\u7136\u800c\uff0c\u5728\u5e02\u573a\u7ecf\u6d4e\u4e2d\uff0cAverage Treatment Effect <\/span>\uff08ATE\uff09<\/span>\u7684\u8bc6\u522b<\/span>\uff08identification\uff09<\/span>\u901a\u5e38\u96be\u4ee5\u6210\u7acb\u3002\u8fd9\u662f\u56e0\u4e3a\u5e02\u573a\u7ecf\u6d4e\u7684\u7279\u70b9\uff0c\u4f8b\u5982\uff1a\u5356\u5bb6\u7684\u7b56\u7565\uff0c\u5546\u54c1\u7684\u4e92\u8865\u6027\u6216\u66ff\u4ee3\u6027\u7b49\u7b49\uff0c\u7834\u574f\u4e86ATE identification\u4e2d\u7684stable unit treatment value assumption<\/span> \uff08SUTVA\uff09<\/span>\u3002\u5177\u4f53\u800c\u8a00\uff0c\u8fd9\u6307\u7684\u662f\uff0c\u5bf9\u4e8e\u4e00\u4e2a\u5b9e\u9a8c\u4e2a\u4f53\u6765\u8bf4\uff0c\u65e0\u8bba\u5b83\u662f\u5904\u4e8etreatment\u8fd8\u662fcontrol\uff0c\u5b83\u7684potential outcomes\u90fd\u4f1a\u4f9d\u8d56\u4e8e\u522b\u7684\u5b9e\u9a8c\u4e2a\u4f53\u7684treatment status\u3002\u6bd4\u5982\uff0c\u4e3a\u4e86\u6bd4\u8f83\u4e24\u4e2a\u5b9a\u4ef7\u7b97\u6cd5\uff0cA\u548cB\uff0c\u5bf9\u5e73\u5747\u9500\u91cf\u7684\u5f71\u54cd\uff0c\u6211\u4eec\u968f\u673a\u5730\u4e3a\u4e00\u7fa4\u9500\u552e\u76f8\u4f3c\u4ea7\u54c1\u7684\u5356\u5bb6\u5206\u914d\u5b9a\u4ef7\u7b97\u6cd5\u3002\u8003\u8651\u4e24\u4e2a\u5356\u5bb6\u548c\u4e24\u79cd\u5206\u914d\u60c5\u666f\uff1a\u60c5\u666f\u4e00\uff1a\u5356\u5bb6\u7532\u7684\u4ef7\u683c\u53d7\u5230\u7b97\u6cd5A\u7684\u5f71\u54cd\u504f\u4f4e\uff0c\u60c5\u666f\u4e8c\uff1a\u5356\u5bb6\u7532\u7684\u4ef7\u683c\u53d7\u5230\u7b97\u6cd5B\u7684\u5f71\u54cd\u504f\u9ad8\u3002\u90a3\u4e48\uff0c\u65e0\u8bba\u5356\u5bb6\u4e59\u662f\u5904\u4e8e\u7b97\u6cd5A\u8fd8\u662f\u7b97\u6cd5B\uff0c\u5b83\u7684potential\u9500\u91cf\u5728\u60c5\u666f\u4e00\u7684\u65f6\u5019\u5fc5\u5b9a\u6bd4\u5728\u60c5\u666f\u4e8c\u7684\u65f6\u5019\u4f4e\u3002\u6362\u53e5\u8bdd\u8bf4\uff0c\u5356\u5bb6\u4e59\u7684potential\u9500\u91cf\u53d7\u5230\u4e86\u5356\u5bb6\u7532\u7684treatment status\u7684\u5f71\u54cd\u3002\u8fd9\u79cd\u60c5\u51b5\u88ab\u79f0\u4e3ainterference\uff0c\u662f\u7834\u574fSUTVA\u7684\u60c5\u51b5\u4e4b\u4e00\uff0c\u4f7f\u5f97\u968f\u673a\u5b9e\u9a8c\u65e0\u6cd5\u8bc6\u522bATE\u3002\u5728\u8fd9\u6b21\u7684\u8bfb\u4e66\u4f1a\u4e2d\uff0c\u6211\u4f1a\u4ecb\u7ecd\u73b0\u9636\u6bb5\u7684\u5de5\u4e1a\u754c\u7684\u5e02\u573a\u5b9e\u9a8c\u662f\u5982\u4f55\u5c1d\u8bd5\u53bb\u89e3\u51b3interference\u3002<\/span><\/section>\n

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

\u63a8\u8350\u53c2\u8003\u6587\u732e <\/strong><\/span><\/p>\n

Abadie, Alberto. 2019. \u201cUsing Synthetic Controls: Feasibility, Data Requirements, and Methodological Aspects.\u201d Journal of Economic Literature. <\/span><\/section>\n
Doudchenko, Nick, Minzhengxiong Zhang, Evgeni Drynkin, Edoardo Airoldi, Vahab Mirrokni, and Jean Pouget-Abadie. 2020. \u201cCausal Inference with Bipartite Designs.\u201d <\/span> <\/span><\/section>\n
Holtz, David, Ruben Lobel, Inessa Liskovich, and Sinan Aral. 2020. \u201cReducing Interference Bias in Online Marketplace Pricing Experiments.\u201d <\/span><\/section>\n
Lechner, Michael. 2011. \u201cThe Estimation of Causal Effects by Difference-in-Difference Methods.\u201d Foundations and Trends\u00ae in Econometrics 4 (3): 165\u2013224. <\/span>https:\/\/doi.org\/10.1561\/0800000014.<\/span> <\/span><\/section>\n
Saveski, Martin, Jean Pouget-Abadie, Guillaume Saint-Jacques, Weitao Duan, Souvik Ghosh, Ya Xu, and Edoardo M Airoldi. 2017. \u201cDetecting Network Effects: Randomizing Over Randomized Experiments.\u201d In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1027\u201335. KDD \u201917. New York, NY, USA: Association for Computing Machinery. <\/span>https:\/\/doi.org\/10.1145\/3097983.3098192.<\/span> <\/span><\/section>\n
Saint-Jacques, Guillaume, Maneesh Varshney, Jeremy Simpson, and Ya Xu. 2019. \u201cUsing Ego-Clusters to Measure Network Effects at LinkedIn.\u201d<\/span><\/section>\n

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

 <\/span><\/p>\n


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

\n
\n
\n

<\/section>\n

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

A Causal View of Bias in Computer Visionvv<\/strong><\/span><\/strong><\/span><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

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

<\/section>\n

\u6c64\u51ef\u534e\uff0c\u5357\u6d0b\u7406\u5de5\u5927\u5b66\uff0c\u7814\u7a76\u65b9\u5411\u4e3a\u8ba1\u7b97\u673a\u89c6\u89c9\u3002<\/span><\/p>\n


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

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


<\/p>\n

\u968f\u7740\u8fd1\u5e74\u7684\u6280\u672f\u53d1\u5c55\uff0c\u76ee\u524d\u57fa\u4e8e\u6df1\u5ea6\u5b66\u4e60\u7684\u673a\u5668\u5b66\u4e60\u7cfb\u7edf\u5728\u5f88\u591a\u8ba1\u7b97\u673a\u89c6\u89c9\u9886\u57df\u7684\u4efb\u52a1\u4e2d\u90fd\u53d6\u5f97\u4e86\u6bd4\u80a9\u751a\u81f3\u8d85\u8fc7\u4eba\u7c7b\u7684\u51c6\u786e\u7387\u3002\u7136\u800c\u8fd9\u79cd\u770b\u4f3c\u5f3a\u5927\u7684\u6027\u80fd\u5374\u88ab\u9650\u5236\u4e8e\u975e\u5e38\u6709\u9650\u7684\u573a\u666f\u548c\u73af\u5883\u4e2d\uff0c\u4efb\u4f55\u6d4b\u8bd5\u6570\u636e\u7684\u6270\u52a8\uff0c\u4e0d\u7ba1\u662f\u5206\u5e03\u4e0a\u7684\u8fd8\u662f\u6570\u636e\u672c\u8eab\u7684\u65b0\u566a\u58f0\uff0c\u90fd\u4f1a\u4e25\u91cd\u5730\u5f71\u54cd\u6a21\u578b\u7684\u6cdb\u5316\u6027\u80fd\u3002\u8fd9\u5176\u5b9e\u5f52\u56e0\u4e8e\uff0c\u76ee\u524d\u7684\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\uff0c\u5728\u5904\u7406\u56fe\u50cf\u548c\u8bed\u8a00\u6570\u636e\u65f6\uff0c\u5176\u5185\u90e8\u5b66\u4e60\u7684\u673a\u5236\u65e0\u6cd5\u88ab\u7406\u89e3\uff0c\u4e5f\u5c31\u662f\u6240\u8c13\u7684\u9ed1\u76d2\u7cfb\u7edf\u3002\u800c\u8fd9\u79cd\u5bf9\u4e2d\u95f4\u5b66\u4e60\u8fc7\u7a0b\u6ca1\u6709\u4efb\u4f55\u6709\u6548\u7ea6\u675f\u548c\u89e3\u91ca\u6027\u8981\u6c42\u7684\u6a21\u578b\uff0c\u5f80\u5f80\u4f1a\u5728\u8bad\u7ec3\u4e2d\u7aed\u5c3d\u6240\u80fd\u7684\u5229\u7528\u6570\u636e\u7684\u4efb\u4f55\u4fe1\u606f\uff0c\u4e5f\u5c31\u5305\u542b\u4e86\u5927\u91cf\u7684\u975e\u56e0\u679c\u6548\u5e94\u7684\u4f2a\u76f8\u5173\uff0c\u6bd4\u5982\u5982\u679c\u96ea\u8c79\u603b\u662f\u51fa\u73b0\u5728\u96ea\u91cc\uff0c\u6a21\u578b\u8bc6\u522b\u96ea\u8c79\u6240\u4f9d\u8d56\u7684\u7279\u5f81\u53ef\u80fd\u5c31\u4e0d\u662f\u96ea\u8c79\u672c\u8eab\uff0c\u800c\u662f\u53bb\u8bc6\u522b\u96ea\u5730\u73af\u5883\u3002\u56e0\u6b64\uff0c\u4e3a\u4e86\u89e3\u51b3\u4e0a\u8ff0\u95ee\u9898\uff0c\u589e\u52a0\u673a\u5668\u5b66\u4e60\u7684\u6cdb\u5316\u6027\u80fd\uff0c\u6211\u4eecMReaL\u5b9e\u9a8c\u5ba4\u8fd1\u5e74\u5f00\u59cb\u5c1d\u8bd5\u8fd0\u7528\u56e0\u679c\u5206\u6790\u4e2d\u7684\u6982\u5ff5\u548c\u601d\u60f3\uff0c\u53bb\u91cd\u65b0\u8ba4\u77e5\u6211\u4eec\u73b0\u6709\u7684\u89c6\u89c9\u6a21\u578b\uff0c\u5e76\u901a\u8fc7\u57fa\u4e8e\u56e0\u679c\u5206\u6790\u7684\u6539\u8fdb\u6765\u53bb\u9664\u5df2\u77e5\u7684\u4f2a\u76f8\u5173<\/span>\uff08spurious correlation\uff09<\/span>\uff0c\u63d0\u53d6\u5176\u76f4\u63a5\u56e0\u679c\u6548\u5e94<\/span>\uff08Direct Effect\uff09<\/span>\u3002\u76ee\u524d\u6211\u4eec\u63d0\u51fa\u7684\u65b9\u6cd5\uff0c\u5728\u573a\u666f\u56fe\u751f\u6210\u548c\u901a\u7528\u7684\u957f\u5c3e\u5206\u5e03\u4e0b\u7684\u5206\u7c7b\u3001\u68c0\u6d4b\u548c\u5206\u5272\u7b49\u95ee\u9898\u4e0a\uff0c\u53d6\u5f97\u4e86\u660e\u663e\u7684\u63d0\u5347\u3002\u5927\u5927\u964d\u4f4e\u4e86\u6a21\u578b\u7ed9\u51fa\u4e0d\u516c\u5e73\u51b3\u7b56\u7684\u53ef\u80fd\u6027\u3002<\/span><\/section>\n

 <\/span><\/p>\n

 <\/span><\/p>\n

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

[1] Tang, Kaihua, et al. “Unbiased scene graph generation from biased training.” Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020.<\/span><\/section>\n
[2] Tang, Kaihua, Jianqiang Huang, and Hanwang Zhang. “Long-tailed classification by keeping the good and removing the bad momentum causal effect.” Advances in Neural Information Processing Systems 33 (2020).<\/span><\/section>\n
[3] Niu, Yulei, et al. “Counterfactual VQA: A Cause-Effect Look at Language Bias.” arXiv preprint arXiv:2006.04315 (2020).<\/span><\/section>\n
[4] Yang, Xu, Hanwang Zhang, and Jianfei Cai. “Deconfounded image captioning: A causal retrospect.” arXiv preprint arXiv:2003.03923 (2020).<\/span><\/section>\n
[5] Zhang, Dong, et al. “Causal intervention for weakly-supervised semantic segmentation.” Advances in Neural Information Processing Systems 33 (2020).<\/span><\/section>\n
[6] Yue, Zhongqi, et al. “Interventional few-shot learning.” Advances in Neural Information Processing Systems 33 (2020).<\/span><\/section>\n

<\/section>\n

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

\u76f4\u64ad\u4fe1\u606f\u4e0e\u62a5\u540d\u65b9\u5f0f<\/strong><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n


<\/p>\n

\u76f4\u64ad\u65f6\u95f4\uff1a\u672c<\/span><\/strong>\u5468\u65e5<\/strong>\uff0812\u670820\u65e5\uff09 9:00-12:00<\/span><\/p>\n


<\/p>\n

\u53c2\u4e0e\u65b9\u5f0f 1\uff1a\u817e\u8baf\u4f1a\u8bae\uff08\u9700\u62a5\u540d\u53c2\u52a0\u7cfb\u5217\u8bfb\u4e66\u4f1a\uff09<\/strong><\/p>\n

\n

\u53c2\u4e0e\u65b9\u5f0f 2\uff1a\u96c6\u667a\u4ff1\u4e50\u90e8B\u7ad9\u76f4\u64ad<\/strong><\/p>\n


<\/p>\n

\u626b\u63cf\u4e0b\u65b9\u4e8c\u7ef4\u7801\uff0c\u70b9\u51fb\u300c\u6211\u8981\u542c\u300d\u62a5\u540d\uff0c\u5185\u9644B\u7ad9\u76f4\u64ad\u5730\u5740\u3002<\/strong><\/p>\n


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

<\/p>\n

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


<\/section>\n

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

<\/p>\n

\n
\n
\n
\n
\n

\u5173\u4e8e\u8bfb\u4e66\u4f1a\u5185\u5bb9\u4ecb\u7ecd\u7684\u66f4\u65b0<\/strong><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

\n


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

\u96c6\u667a\u4ff1\u4e50\u90e8\u8054\u5408\u667a\u6e90\u793e\u533a\u53d1\u8d77\u4e86\u56e0\u679c\u79d1\u5b66\u4e0eCausal AI\u8bfb\u4e66\u4f1a\u53d7\u5230\u4e86\u56e0\u679c\u79d1\u5b66\u9886\u57df\u4e00\u7ebf\u79d1\u7814\u5de5\u4f5c\u8005\u7684\u5e7f\u6cdb\u8ba4\u53ef\uff0c\u6211\u4eec\u4e5f\u6df1\u6df1\u7684\u611f\u53d7\u5230\u4e86\u9752\u5e74\u79d1\u5b66\u5de5\u4f5c\u8005\u63a8\u52a8\u8be5\u9886\u57df\u53d1\u5c55\u7684\u70ed\u60c5\u3002<\/span>\u76ee\u524d\u56e0\u679c\u79d1\u5b66\u4e0eCausal AI\u8bfb\u4e66\u4f1a\u5df2\u7ecf\u6709220+\u7684\u670b\u53cb\u62a5\u540d\uff0c\u5176\u4e2d\u7855\u535a\u7684\u6bd4\u4f8b\u63a5\u8fd180%\u3002<\/span><\/span><\/p>\n

<\/span><\/p>\n<\/h2>\n

 <\/span><\/p>\n

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

\u5728\u8bfb\u4e66\u4f1a\u4e2d\u7684\u53c2\u4e0e\u8005\u4ee5\u79d1\u7814\u5de5\u4f5c\u8005\u5c45\u591a\uff0c\u6e05\u534e\u5927\u5b66\u3001\u5317\u4eac\u5927\u5b66\u3001\u56fd\u9632\u79d1\u6280\u5927\u5b66\u3001\u6d59\u6c5f\u5927\u5b66\u3001\u590d\u65e6\u5927\u5b66\u3001\u4e2d\u5c71\u5927\u5b66\u7b49\u56fd\u5185\u9ad8\u6821\u7684\u5b66\u751f\u5c45\u591a\uff0c\u4e5f\u6709\u8bb8\u591a\u4e00\u7ebf\u4e92\u8054\u7f51\u5305\u62ec\u8c37\u6b4cX\u3001FackBook\u3001\u6ef4\u6ef4\u3001\u817e\u8baf\u3001\u963f\u91cc\u3001\u62fc\u591a\u591a\u7b49\u5927\u5382\u7684\u5de5\u7a0b\u5e08\u4e5f\u53c2\u4e0e\u5176\u4e2d\u3002<\/span><\/p>\n


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

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

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

\u6b22\u8fce\u5927\u5bb6\u52a0\u5165\u5176\u4e2d\uff0c\u73b0\u5728\u52a0\u5165\u8bfb\u4e66\u4f1a\u7684\u6210\u5458\u5c06\u4f1a\u4f5c\u4e3a\u56e0\u679c\u793e\u533a\u7684\u79cd\u5b50\u7528\u6237\u957f\u671f\u8fd0\u8425\uff0c\u5c06\u53ef\u4ee5\u514d\u8d39\u4eab\u53d7\u96c6\u667a\u4ff1\u4e50\u90e8\u540e\u7eed\u56e0\u679c\u76f8\u5173\u4e3b\u9898\u7684\u8bfb\u4e66\u4f1a<\/strong>\uff0c\u5982\u679c\u4f60\u5fc3\u52a8\u4e86\uff0c\u5c31\u70b9\u51fb\u4e0b\u9762\u7684\u94fe\u63a5\u62a5\u540d\u5427~<\/span><\/p>\n

 <\/span><\/p>\n

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

\u65f6\u95f4\uff1a<\/span><\/strong>9\u670820\u65e5\u8d77\uff0c\u6bcf\u5468\u65e5\u665a19:00-21:00\uff0c\u6301\u7eed\u7ea62-3\u4e2a\u6708<\/span><\/section>\n
\u6a21\u5f0f\uff1a<\/span><\/strong>\u7ebf\u4e0a\u95ed\u95e8\u8bfb\u4e66\u4f1a\uff1b\u6536\u8d39-\u9000\u6b3e\u7684\u4fdd\u8bc1\u91d1\u6a21\u5f0f\uff1b\u8bfb\u4e66\u4f1a\u6210\u5458\u8ba4\u9886\u89e3\u8bfb\u8bba\u6587<\/span><\/section>\n
\u8d39\u7528\uff1a<\/span><\/strong>299\/\u4eba<\/span><\/section>\n

 <\/span><\/p>\n

\u4e86\u89e3\u8bfb\u4e66\u4f1a\u5177\u4f53\u89c4\u5219\u3001\u62a5\u540d\u8bfb\u4e66\u4f1a\u8bf7\u70b9\u51fb\u4e0b\u65b9\u6587\u7ae0\uff1a<\/span><\/p>\n

\u56e0\u679c\u79d1\u5b66\u4e0e Causal AI \u7cfb\u5217\u8bfb\u4e66\u4f1a | \u4f17\u5305\u51fa\u4e66<\/span><\/a><\/section>\n


<\/p>\n

<\/p>\n

\u76ee\u524d\u8bfb\u4e66\u4f1a\u5df2\u7ecf\u6709\u8d85\u8fc7130\u4f59\u4eba\u7684\u6d77\u5185\u5916\u9ad8\u6821\u79d1\u7814\u9662\u6240\u7684\u4e00\u7ebf\u79d1\u7814\u5de5\u4f5c\u8005\u4ee5\u53ca\u4e92\u8054\u7f51\u4e00\u7ebf\u4ece\u4e1a\u4eba\u5458\u53c2\u4e0e\uff0c\u5982\u679c\u4f60\u4e5f\u5bf9\u8fd9\u4e2a\u4e3b\u9898\u611f\u5174\u8da3\uff0c\u5c31\u5feb\u52a0\u5165\u6211\u4eec\u5427\uff01<\/span><\/p>\n


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

<\/section>\n

\u9488\u5bf9\u8bfb\u4e66\u4f1a\u7684\u4e3b\u9898\uff0c\u7531\u53d1\u8d77\u4eba\u9f9a\u9e64\u626c\u8bbe\u7f6e\u597d\u4e86\u5185\u5bb9\u6846\u67b6\uff0c\u6bcf\u4e2a\u4e3b\u9898\u4e0b\u6709\u4e00\u4e2a\u8d1f\u8d23\u4eba\u6765\u8d1f\u8d23\u7ef4\u62a4\u7ec4\u7ec7\u76f8\u5173\u5185\u5bb9\uff0c\u76ee\u524d\u5df2\u7ecf\u5b9a\u597d\u7684\u5982\u56fe\u6240\u793a\uff0c\u6b22\u8fce\u5bf9\u4e3b\u9898\u611f\u5174\u8da3\u7684\u8054\u7cfb\u76f8\u5173\u8d1f\u8d23\u4eba\uff0c\u4ee5\u53ca\u6765\u8ba4\u9886\u76f8\u5173\u4e3b\u9898~<\/span><\/p>\n


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

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


<\/section>\n
\u63a8\u8350\u9605\u8bfb<\/span><\/strong><\/strong><\/span><\/section>\n