{"id":35966,"date":"2022-07-20T18:16:57","date_gmt":"2022-07-20T10:16:57","guid":{"rendered":"https:\/\/swarma.org\/?p=35966"},"modified":"2022-07-20T18:16:57","modified_gmt":"2022-07-20T10:16:57","slug":"%e9%bb%84%e6%b5%b7%e5%b9%b3%ef%bc%9a%e7%a5%9e%e7%bb%8f%e7%bd%91%e7%bb%9c%e7%9a%84%e7%bb%9f%e8%ae%a1%e5%8a%9b%e5%ad%a6%e8%af%be%e7%a8%8b-50%e4%ba%ba%e5%85%8d%e8%b4%b9%e5%90%8d%e9%a2%9d","status":"publish","type":"post","link":"https:\/\/swarma.org\/?p=35966","title":{"rendered":"\u9ec4\u6d77\u5e73\uff1a\u795e\u7ecf\u7f51\u7edc\u7684\u7edf\u8ba1\u529b\u5b66\u8bfe\u7a0b | 50\u4eba\u514d\u8d39\u540d\u989d"},"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

\u4e3a\u4e86\u5e2e\u52a9\u5b66\u751f\u5b66\u4e60\u7edf\u8ba1\u529b\u5b66\u7684\u57fa\u672c\u539f\u7406\u53ca\u5176\u5728\u7406\u89e3\u795e\u7ecf\u7f51\u7edc\u5185\u90e8\u5de5\u4f5c\u539f\u7406\u7684\u5e94\u7528\uff0c\u4e2d\u5c71\u5927\u5b66\u6559\u6388\u3001PMI Lab\u7684\u9ec4\u6d77\u5e73\u8001\u5e08\u7ec4\u7ec7\u4e86\u300a\u795e\u7ecf\u7f51\u7edc\u7684\u7edf\u8ba1\u529b\u5b66\u300b\u5728\u7ebf\u8bfe\u7a0b\uff0c\u6682\u5b9a\u4e8e2022\u5e749\u670817\u65e5\u8d77\u6bcf\u5468\u516d14:30-16:00\uff08\u8282\u5047\u65e5\u9664\u5916\uff09\u8fdb\u884c\uff0c\u8bfe\u7a0b\u4ece2022\u5e749\u6708\u6301\u7eed\u52302023\u5e746\u6708\u3002<\/strong><\/p>\n<\/section>\n


<\/strong><\/section>\n
\u8bfe\u7a0b\u62db\u653650\u540d\u6b63\u5f0f\u5b66\u5458\uff0c\u5177\u4f53\u7533\u8bf7\u6761\u4ef6\u3001\u6d41\u7a0b\u89c1\u6b63\u6587\u3002\u7533\u8bf7\u622a\u6b62\u65f6\u95f4\u4e3a2022\u5e748\u670831\u65e5\uff0c\u8bf7\u611f\u5174\u8da3\u7684\u540c\u5b66\u5c3d\u5feb\u63d0\u4ea4\u6750\u6599\u3002<\/strong><\/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


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


<\/p>\n

\n
\n
\n
\n
\n

<\/section>\n

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

\u8bfe\u7a0b\u80cc\u666f<\/span><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

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

<\/section>\n

\u8bfe\u7a0b\u6d89\u53ca\u9ec4\u6d77\u5e73\u8001\u5e08\u6700\u65b0\u51fa\u7248\u7684\u4e66\u7c4d\u300aStatistical Mechanics of Neural Networks\u300b\u7684\u5927\u90e8\u5206\u5185\u5bb9\uff0c\u76ee\u6807\u662f\u5b66\u4e60\u7edf\u8ba1\u529b\u5b66\u7684\u57fa\u672c\u539f\u7406\u53ca\u5176\u5728\u7406\u89e3\u795e\u7ecf\u7f51\u7edc\u5185\u90e8\u5de5\u4f5c\u539f\u7406\u7684\u5e94\u7528\u3002<\/span><\/p>\n


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


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

\n
\n
\n
\n
\n

<\/section>\n

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

\u8d1f\u8d23\u4eba\u4ecb\u7ecd<\/span><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

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

<\/section>\n

<\/p>\n

\u9ec4\u6d77\u5e73<\/span><\/strong>\uff0c\u4e2d\u5c71\u5927\u5b66\u7269\u7406\u5b66\u9662\u6559\u6388\u3002\u672c\u79d1\u6bd5\u4e1a\u4e8e\u4e2d\u5c71\u5927\u5b66\u7406\u5de5\u5b66\u9662\uff0c\u535a\u58eb\u6bd5\u4e1a\u4e8e\u4e2d\u56fd\u79d1\u5b66\u9662\u7406\u8bba\u7269\u7406\u7814\u7a76\u6240\uff0c\u968f\u540e\u5728\u9999\u6e2f\u79d1\u6280\u5927\u5b66\u7269\u7406\u7cfb\u3001\u4e1c\u4eac\u5de5\u4e1a\u5927\u5b66\u8ba1\u7b97\u667a\u80fd\u7cfb (2012\u5e74\u83b7\u65e5\u672c\u5b66\u672f\u632f\u5174\u4f1a\u8d44\u52a9) \u4ee5\u53ca\u65e5\u672c\u7406\u5316\u5b66\u7814\u7a76\u6240 (RIKEN) \u8111\u79d1\u5b66\u4e2d\u5fc3\u4ece\u4e8b\u7edf\u8ba1\u7269\u7406\u4e0e\u673a\u5668\u5b66\u4e60\u3001 \u795e\u7ecf\u8ba1\u7b97\u4ea4\u53c9\u7684\u57fa\u7840\u7406\u8bba\u7814\u7a76\uff0c2017\u5e74\u56e0\u5728\u65e0\u76d1\u7763\u5b66\u4e60\u65b9\u9762\u7684\u7814\u7a76\u83b7\u5f97 RIKEN \u6770\u51fa\u7814\u7a76\u5956\u3002\u4e8e2018\u5e74\u5165\u9009\u4e2d\u5c71\u5927\u5b66\u767e\u4eba\u8ba1\u5212\uff0c\u5728\u7269\u7406\u5b66\u9662\u7ec4\u5efa\u4e86\u201c\u7269\u7406\u3001\u673a\u5668\u4e0e\u667a\u80fd\u201d \uff08PMI\uff09\u7814\u7a76\u5c0f\u7ec4\uff0c\u4e13\u6ce8\u4e8e\u5404\u79cd\u795e\u7ecf\u8ba1\u7b97\u7684\u7406\u8bba\u57fa\u7840\uff0c\u957f\u671f\u76ee\u6807\u662f\u4f7f\u7528\u57fa\u4e8e\u7269\u7406\u7684\u8fd1\u4f3c\u6765\u63ed\u793a\u673a\u5668\u53ca\u5927\u8111\u667a\u80fd\u7684\u57fa\u672c\u539f\u7406\u3002\u66fe\u4e3b\u6301\u56fd\u5bb6\u81ea\u7136\u79d1\u5b66\u57fa\u91d1\u9752\u5e74\u57fa\u91d1\u3001\u4f18\u79c0\u9752\u5e74\u57fa\u91d1\u7b49\u56fd\u5bb6\u7ea7\u9879\u76ee\u3002<\/span><\/section>\n

PMI Lab\uff1ahttps:\/\/www.labxing.com\/hphuang2018<\/span><\/p>\n


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

\n
\n
\n
\n
\n

<\/section>\n

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

\u6b63\u5f0f\u5b66\u5458\u7533\u8bf7\u8981\u6c42\u4e0e\u6d41\u7a0b<\/span><\/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\u540d\u989d\uff1a<\/span><\/strong>\u8bfe\u7a0b\u62db\u653650\u540d\u6b63\u5f0f\u5b66\u5458\u3002\u6b63\u5f0f\u5b66\u5458\u53d7\u8bfe\u7a0b\u8d1f\u8d23\u4eba\u9ec4\u6d77\u5e73\u8001\u5e08\u8fdb\u884c\u4e25\u683c\u7684\u8bfe\u7a0b\u5b66\u4e60\u7ba1\u7406\uff0c\u5b8c\u6210\u8bfe\u7a0b\u4f5c\u4e1a\u3001\u8bfe\u7a0b\u5c0f\u9879\u76ee\u8bba\u6587\u7b49\u3002<\/span><\/p>\n


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

\u57f9\u517b\u76ee\u6807\uff1a<\/span><\/strong>\u57f9\u517b\u4e00\u6279\u6709\u671b\u5728\u795e\u7ecf\u7f51\u7edc\u7406\u8bba\u6df1\u8015\u7684\u9752\u5e74\u5b66\u8005\uff08\u4fa7\u91cd\u5b66\u751f\uff09<\/span><\/p>\n


<\/p>\n

\u7533\u8bf7\u4eba\u8981\u6c42\uff1a<\/span><\/strong>\u5bf9\u7edf\u8ba1\u2f12\u5b66\u3001\u795e\u7ecf\u2f79\u7edc\u53ca\u8111\u79d1\u5b66\u4ea4\u53c9\u611f\u5174\u8da3\u7684\u7814\u7a76\u2f63\/\u672c\u79d1\u2f63\/\u535a\u2f20\u540e\u5747\u53ef\u62a5\u540d\u8bfe\u7a0b\uff0c\u9700\u5177\u5907\u2fbc\u7b49\u6570\u5b66\u3001\u6982\u7387\u8bba\u3001\u7ebf\u6027\u4ee3\u6570\u3001python\/C\u8bed\u2f94\u3001\u7edf\u8ba1\u2f12\u5b66\u57fa\u7840\uff08\u4f8b\u5982\u6559\u79d1\u4e66\uff09\u3002\u6709\u795e\u7ecf\u2f79\u7edc\u6216\u8ba1\u7b97\u795e\u7ecf\u79d1\u5b66\u77e5\u8bc6\u8005\u4f18\u5148\u3002<\/span><\/p>\n


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

\u7533\u8bf7\u622a\u2f4c\u2f47\u671f\uff1a2022\u5e748\u2f4931\u2f47<\/span><\/strong>\uff08\u9700\u9644\u7b80\u5386\u2f84huanghp7@mail.sysu.edu.cn\uff09\u3002<\/span><\/p>\n


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

\u7533\u8bf7\u6210\u529f\u5b66\u5458\u798f\u5229\uff1a<\/span><\/strong>\u672c\u8bfe\u7a0b\u4f1a\u7531\u96c6\u667a\u5b66\u56ed\u8fdb\u884c\u514d\u8d39\u76f4\u64ad\uff0c\u6536\u8d39\u5f55\u64ad\u3002\u4f46\u662f\u7ecf\u9ec4\u6d77\u5e73\u8001\u5e08\u7b5b\u9009\uff0c\u88ab\u6210\u529f\u5f55\u53d6\u7684\u6b63\u5f0f\u5b66\u5458\u53ef\u514d\u8d39\u83b7\u53d6\u89c6\u9891\u5f55\u64ad\u6743\u9650\u3002\u5177\u4f53\u5728\u786e\u8ba4\u5b66\u5458\u540d\u5355\u540e\uff0c\u4f1a\u7edf\u4e00\u5f00\u901a\u3002<\/span><\/p>\n


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


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

\n
\n
\n
\n
\n

<\/section>\n

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

\u8bfe\u7a0b\u56de\u653e<\/span><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

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

<\/section>\n

\u672c\u8bfe\u7a0b\u7531\u96c6\u667a\u5b66\u56ed\u8fdb\u884c\u514d\u8d39\u76f4\u64ad\uff0c\u6536\u8d39\u5f55\u64ad\u3002\u8bfe\u7a0b\u5b9a\u4ef7\uff1a499\uff0c\u65f6\u95f4\u5468\u671f\u5728 2022.09-2023.06 \u6301\u7eed\u66f4\u65b0\u3002\u4ece9\u6708\u5f00\u59cb\u66f4\u65b0\uff0c\u73b0\u5728\u5904\u4e8e\u9884\u552e\u9636\u6bb5\u3002\u672a\u6210\u4e3a\u6b63\u5f0f\u5b66\u5458\u7684\u540c\u5b66\uff0c\u53ef\u4ed8\u8d39\u62a5\u540d\u5f55\u64ad\uff0c\u53c2\u4e0e\u5b66\u4e60\u3002<\/span><\/p>\n


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

\u8bfe\u7a0b\u65f6\u95f4\uff1a<\/span><\/strong>\u4ece2022\u5e749\u670817\u65e5\u8d77\uff0c\u6bcf\u5468\u516d 14:30-16:00\uff08\u8282\u5047\u65e5\u9664\u5916\uff09<\/span><\/p>\n


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

<\/p>\n

\u626b\u7801\u4ed8\u8d39\u62a5\u540d\u8bfe\u7a0b<\/span><\/p>\n


<\/p>\n

\u4ed8\u8d39\u6d41\u7a0b\uff1a<\/span><\/strong><\/span><\/section>\n
    \n
  1. \n
    \u626b\u7801\u4ed8\u8d39\uff1b<\/span><\/section>\n<\/li>\n
  2. \n
    \u8bfe\u7a0b\u9875\u9762\u6dfb\u52a0\u5b66\u5458\u767b\u8bb0\u8868\uff0c\u6dfb\u52a0\u52a9\u6559\u5fae\u4fe1\u5165\u7fa4\uff1b<\/span><\/section>\n<\/li>\n
  3. \n

    \u8bfe\u7a0b\u53ef\u5f00\u53d1\u7968\u3002<\/span><\/p>\n<\/li>\n<\/ol>\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

    \u4e66\u7c4d\u4ecb\u7ecd<\/span><\/strong><\/strong><\/p>\n<\/section>\n

    \n

    <\/section>\n

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

    <\/section>\n

    \u672c\u4e66\u6db5\u76d6\u4e86\u7528\u4e8e\u7406\u89e3\u795e\u7ecf\u7f51\u7edc\u539f\u7406\u7684\u5fc5\u8981\u7edf\u8ba1\u529b\u5b66\u77e5\u8bc6\uff0c\u5305\u62ec\u590d\u672c\u65b9\u6cd5\u3001\u7a7a\u8154\u65b9\u6cd5\u3001\u5e73\u5747\u573a\u8fd1\u4f3c\u3001\u53d8\u5206\u6cd5\u3001\u968f\u673a\u80fd\u91cf\u6a21\u578b\u3001Nishimori\u6761\u4ef6\u3001\u52a8\u529b\u5b66\u5e73\u5747\u573a\u7406\u8bba\u3001\u5bf9\u79f0\u6027\u7834\u7f3a\u3001\u968f\u673a\u77e9\u9635\u7406\u8bba\u7b49\uff0c\u540c\u65f6\u8be6\u7ec6\u63cf\u8ff0\u4e86\u76d1\u7763\u5b66\u4e60\u3001\u65e0\u76d1\u7763\u5b66\u4e60\u3001\u8054\u60f3\u8bb0\u5fc6\u7f51\u7edc\u3001\u611f\u77e5\u5668\u7f51\u7edc\u3001\u968f\u673a\u5faa\u73af\u7f51\u7edc\u7b49\u795e\u7ecf\u7f51\u7edc\u53ca\u5176\u529f\u80fd\u7684\u7269\u7406\u6a21\u578b\u4ee5\u53ca\u89e3\u6790\u7406\u8bba\u3002\u672c\u4e66\u901a\u8fc7\u7b80\u6d01\u7684\u6a21\u578b\u5c55\u793a\u4e86\u795e\u7ecf\u7f51\u7edc\u539f\u7406\u7684\u6570\u5b66\u7f8e\u548c\u7269\u7406\u6df1\u5ea6\uff0c\u5e76\u4ecb\u7ecd\u4e86\u76f8\u5173\u5386\u53f2\u548c\u5c55\u671b\u672a\u6765\u7814\u7a76\u7684\u91cd\u8981\u8bfe\u9898\uff0c\u53ef\u4f9b\u5bf9\u795e\u7ecf\u7f51\u7edc\u539f\u7406\u611f\u5174\u8da3\u7684\u5b66\u751f\u3001\u7814\u7a76\u4eba\u5458\u4ee5\u53ca\u5de5\u7a0b\u5e08\u9605\u8bfb\u53c2\u8003\u3002<\/span><\/p>\n


    <\/p>\n

    \u5173\u952e\u8bcd\uff1a\u7edf\u8ba1\u529b\u5b66\uff0c\u795e\u7ecf\u7f51\u7edc\uff0c\u673a\u5668\u5b66\u4e60\uff0c\u968f\u673a\u77e9\u9635\uff0c\u975e\u7ebf\u6027\u52a8\u529b\u5b66<\/span><\/p>\n


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

    <\/section>\n

    Statistical Mechanics of Neural Networks<\/span><\/p>\n


    <\/p>\n

    \u672c\u4e66\u6d77\u5916\u7248\u7531 Springer \u53d1\u884c\uff0c\u76ee\u524d\u53ef\u5728 Amazon \u5e73\u53f0\u8d2d\u4e70\u3002\u56fd\u5185\u7531\u9ad8\u6559\u51fa\u7248\u793e\u53d1\u884c\uff0c\u9884\u8ba18\u6708\u4e2d\u65ec\u4e66\u7c4d\u4e0a\u67b6\uff0c\u53ef\u5728\u56fd\u5185\u5404\u5927\u5e73\u53f0\u8d2d\u4e70\u3002<\/span><\/p>\n


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

    \u4e66\u7c4d\u76ee\u5f55\uff08\u8be6\u7248\uff09\uff1a<\/span><\/p>\n

    Chapter 1:  Introduction<\/span><\/section>\n

    Chapter 2:  Spin Glass Models and Cavity Method<\/span><\/p>\n

      \n
    • \n

      2.1 Multi-spin Interaction Models<\/span><\/p>\n<\/li>\n

    • \n

      2.2 Cavity Method<\/span><\/p>\n<\/li>\n

    • \n
      2.3 From Cavity Method to Message Passing Algorithms<\/span><\/section>\n<\/li>\n<\/ul>\n

      Chapter 3:  Variational Mean-Field Theory and Belief Propagation<\/span><\/p>\n

        \n
      • \n

        3.1 Variational Method<\/span><\/p>\n<\/li>\n

      • \n

        3.2 Variational Free Energy<\/span><\/p>\n<\/li>\n

      • \n
        3.3 Mean-Field Inverse Ising Problem<\/span><\/section>\n<\/li>\n<\/ul>\n

        Chapter 4:  Monte Carlo Simulation Methods<\/span><\/p>\n

          \n
        • \n

          4.1 Monte Carlo Method<\/span><\/p>\n<\/li>\n

        • \n

          4.2 Importance Sampling<\/span><\/p>\n<\/li>\n

        • \n

          4.3 Markov Chain Sampling<\/span><\/p>\n<\/li>\n

        • \n
          4.4 Monte Carlo Simulations in Statistical Physics<\/span><\/section>\n<\/li>\n<\/ul>\n

          Chapter 5:  High-Temperature Expansion<\/span><\/p>\n

            \n
          • \n

            5.1 Statistical Physics Setting<\/span><\/p>\n<\/li>\n

          • \n

            5.2 High-Temperature Expansion<\/span><\/p>\n<\/li>\n

          • \n
            5.3 Properties of the TAP Equation<\/span><\/section>\n<\/li>\n<\/ul>\n

            Chapter 6:  Nishimori Line<\/span><\/p>\n

              \n
            • \n

              6.1 Model Setting<\/span><\/p>\n<\/li>\n

            • \n

              6.2 Exact Result for Internal Energy<\/span><\/p>\n<\/li>\n

            • \n
              6.3 Proof of No RSB Effects on the Nishimori Line<\/span><\/section>\n<\/li>\n<\/ul>\n

              Chapter 7:  Random Energy Model<\/span><\/p>\n

                \n
              • \n

                7.1 Model Setting<\/span><\/p>\n<\/li>\n

              • \n
                7.2 Phase Diagram<\/span><\/section>\n<\/li>\n<\/ul>\n

                Chapter 8:  Statistical Mechanical Theory of Hopfifield Model<\/span><\/p>\n

                  \n
                • \n

                  8.1 Hopfifield Model<\/span><\/p>\n<\/li>\n<\/ul>\n

                    \n
                  • \n

                    8.2 Replica Method<\/span><\/p>\n<\/li>\n<\/ul>\n

                      \n
                    • \n

                      8.3 Phase Diagram<\/span><\/p>\n<\/li>\n<\/ul>\n

                        \n
                      • \n
                        8.4 Hopfifield Model with Arbitrary Hebbian Length<\/span><\/section>\n<\/li>\n<\/ul>\n

                        Chapter 9:  Replica Symmetry and Replica Symmetry Breaking<\/span><\/p>\n

                          \n
                        • \n

                          9.1 Generalized Free Energy and Complexity of States<\/span><\/p>\n<\/li>\n<\/ul>\n

                            \n
                          • \n

                            9.2 Applications to Constraint Satisfaction Problems<\/span><\/p>\n<\/li>\n<\/ul>\n

                              \n
                            • \n
                              9.3 More Steps of Replica Symmetry Breaking<\/span><\/section>\n<\/li>\n<\/ul>\n

                              Chapter 10:  Statistical Mechanics of Restricted Boltzmann Machine<\/span><\/p>\n

                                \n
                              • \n

                                10.1 Boltzmann Machine<\/span><\/p>\n<\/li>\n<\/ul>\n

                                  \n
                                • \n

                                  10.2 Restricted Boltzmann Machine<\/span><\/p>\n<\/li>\n<\/ul>\n

                                    \n
                                  • \n

                                    10.3 Free Energy Calculation<\/span><\/p>\n<\/li>\n<\/ul>\n

                                      \n
                                    • \n

                                      10.4 Thermodynamic Quantities Related to Learning<\/span><\/p>\n<\/li>\n<\/ul>\n

                                        \n
                                      • \n

                                        10.5 Stability Analysis<\/span><\/p>\n<\/li>\n<\/ul>\n

                                          \n
                                        • \n
                                          10.6 Variational Mean-Field Theory for Training Binary RBMs<\/span><\/section>\n<\/li>\n<\/ul>\n

                                          Chapter 11:  Simplest Model of Unsupervised Learning with Binary<\/span><\/p>\n

                                            \n
                                          • \n

                                            11.1 Model Setting<\/span><\/p>\n<\/li>\n<\/ul>\n

                                              \n
                                            • \n

                                              11.2 Derivation of sMP and AMP Equations<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                \n
                                              • \n

                                                11.3 Replica Computation<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                  \n
                                                • \n

                                                  11.4 Phase Transitions<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                    \n
                                                  • \n
                                                    11.5 Measuring the Temperature of Dataset<\/span><\/section>\n<\/li>\n<\/ul>\n

                                                    Chapter 12:  Inherent-Symmetry Breaking in Unsupervised Learning<\/span><\/p>\n

                                                      \n
                                                    • \n

                                                      12.1 Model Setting<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                        \n
                                                      • \n

                                                        12.2 Phase Diagram<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                          \n
                                                        • \n
                                                          12.3 Hyper-Parameters Inference<\/span><\/section>\n<\/li>\n<\/ul>\n

                                                          Chapter 13:  Mean-Field Theory of Ising Perceptron<\/span><\/p>\n

                                                            \n
                                                          • \n

                                                            13.1 Ising Perceptron model<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                              \n
                                                            • \n

                                                              13.2 Message-Passing-Based Learning<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                                \n
                                                              • \n
                                                                13.3 Replica Analysis<\/span><\/section>\n<\/li>\n<\/ul>\n

                                                                Chapter 14:  Mean-Field Model of Multi-layered Perceptron<\/span><\/p>\n

                                                                  \n
                                                                • \n

                                                                  14.1 Random Active Path Model<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                                    \n
                                                                  • \n

                                                                    14.2 Mean-Field Training Algorithms<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                                      \n
                                                                    • \n
                                                                      14.3 Spike and Slab Model<\/span><\/section>\n<\/li>\n<\/ul>\n

                                                                      Chapter 15:  Mean-Field Theory of Dimension Reduction in Neural Networks<\/span><\/p>\n

                                                                        \n
                                                                      • \n

                                                                        15.1 Mean-Field Model<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                                          \n
                                                                        • \n

                                                                          15.2 Linear Dimensionality and Correlation Strength<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                                            \n
                                                                          • \n
                                                                            15.3 Dimension Reduction with Correlated Synapses<\/span><\/section>\n<\/li>\n<\/ul>\n

                                                                            Chapter 16:  Chaos Theory of Random Recurrent Neural Networks<\/span><\/p>\n

                                                                              \n
                                                                            • \n

                                                                              16.1 Spiking and Rate Models<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                                                \n
                                                                              • \n

                                                                                16.2 Dynamical Mean-Field Theory<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                                                  \n
                                                                                • \n

                                                                                  16.3 Lyapunov Exponent and Chaos<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                                                    \n
                                                                                  • \n

                                                                                    16.4 Excitation-Inhibition Balance Theory<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                                                      \n
                                                                                    • \n
                                                                                      16.5 Training Recurrent Neural Networks<\/span><\/section>\n<\/li>\n<\/ul>\n

                                                                                      Chapter 17:  Statistical Mechanics of Random Matrices<\/span><\/p>\n

                                                                                        \n
                                                                                      • \n

                                                                                        17.1 Spectral Density<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                                                          \n
                                                                                        • \n

                                                                                          17.2 Replica Method and Semi-circle Law<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                                                            \n
                                                                                          • \n

                                                                                            17.3 Cavity Approach and Marchenko<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                                                              \n
                                                                                            • \n
                                                                                              17.4 Spectral Densities of Random Asymmetric Matrices<\/span><\/section>\n<\/li>\n<\/ul>\n

                                                                                              Chapter 18:  Perspectives<\/span><\/p>\n


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

                                                                                              <\/section>\n
                                                                                              \u6559\u79d1\u4e66\uff1aStatistical Mechanics of Phase Transitions (Oxford Science Publications) 1st Edition<\/span><\/section>\n

                                                                                              <\/span><\/section>\n
                                                                                              \u5728\u7ebf\u8bfe\u7a0b\u9875\u9762\uff1a<\/span><\/section>\n
                                                                                              https:\/\/www.labxing.com\/lab\/666\/news\/677<\/span><\/section>\n

                                                                                              <\/section>\n

                                                                                              <\/section>\n
                                                                                              \u70b9\u51fb\u201c\u9605\u8bfb\u539f\u6587\u201d\uff0c\u62a5\u540d\u8bfe\u7a0b<\/span><\/strong><\/section>\n<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"

                                                                                              \u5bfc\u8bed \u4e3a\u4e86\u5e2e\u52a9\u5b66\u751f\u5b66\u4e60\u7edf\u8ba1\u529b\u5b66\u7684\u57fa\u672c\u539f\u7406\u53ca\u5176\u5728\u7406\u89e3\u795e\u7ecf\u7f51\u7edc\u5185\u90e8\u5de5\u4f5c\u539f\u7406\u7684\u5e94\u7528\uff0c\u4e2d\u5c71\u5927\u5b66\u6559\u6388\u3001PMI Lab\u7684\u9ec4\u6d77\u5e73\u8001\u5e08\u7ec4\u7ec7\u4e86\u300a\u795e\u7ecf\u7f51\u7edc\u7684\u7edf\u8ba1\u529b\u5b66\u300b\u5728\u7ebf\u8bfe\u7a0b\uff0c\u6682\u5b9a\u4e8e2022\u5e749\u670817\u65e5\u8d77\u6bcf\u5468\u516d14:30-16:00\uff08\u8282\u5047\u65e5\u9664\u5916\uff09\u8fdb\u884c\uff0c\u8bfe\u7a0b\u4ece2022\u5e749\u6708\u6301\u7eed\u52302023\u5e746\u6708\u3002 \u8bfe\u7a0b\u62db\u653650\u540d\u6b63\u5f0f\u5b66\u5458\uff0c…<\/p>\n","protected":false},"author":1,"featured_media":35953,"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\/35966"}],"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"}],"author":[{"embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=35966"}],"version-history":[{"count":0,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/posts\/35966\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/media\/35953"}],"wp:attachment":[{"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=35966"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=35966"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=35966"},{"taxonomy":"special","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fspecial&post=35966"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}