{"id":152809,"date":"2018-09-06T06:57:31","date_gmt":"2018-09-05T22:57:31","guid":{"rendered":"\/\/m.iemloyee.com\/?p=152809"},"modified":"2018-09-06T15:50:57","modified_gmt":"2018-09-06T07:50:57","slug":"%e9%99%a4%e4%ba%86%e6%89%93dota%e4%b8%8b%e5%9b%b4%e6%a3%8b-%e6%9c%ba%e5%99%a8%e5%ad%a6%e4%b9%a0%e5%b7%b2%e5%b8%ae%e5%8a%a9%e6%88%91%e4%bb%ac%e5%8f%96%e5%be%97%e4%ba%86%e8%bf%99%e4%ba%9b%e6%9d%90","status":"publish","type":"post","link":"\/\/m.iemloyee.com\/?p=152809","title":{"rendered":"\u9664\u4e86\u6253DOTA\u4e0b\u56f4\u68cb \u673a\u5668\u5b66\u4e60\u5df2\u5e2e\u52a9\u6211\u4eec\u53d6\u5f97\u4e86\u8fd9\u4e9b\u6750\u6599\u79d1\u7814\u8fdb\u5c55"},"content":{"rendered":"

\u6750\u6599\u4eba\u7ee7\u7eed\u63a8\u51fa\u8ba1\u7b97\u6750\u6599\u6210\u679c\u6c47\u7f16\uff08\u6708\u520a\uff09\uff0c\u62a5\u9053\u8ba1\u7b97\u6750\u6599\u76f8\u5173\u91cd\u5927\u6210\u679c\u3002\u672c\u7bc7\u4e3a\u673a\u5668\u5b66\u4e60\u4e13\u520a\u3002<\/p>\n

1. \u673a\u5668\u5b66\u4e60\u7528\u4e8e\u9884\u6d4b\u65e0\u673a\u6750\u6599\u7684\u6027\u80fd<\/strong><\/p>\n

\"\"<\/p>\n

\u56fe<\/strong>1 Al-Ni-Zr<\/strong>\u4e09\u5143\u533a\u73bb\u7483\u6210\u5f62\u80fd\u529b\u7684\u5b9e\u9a8c\u6d4b\u91cf\u7ed3\u679c<\/strong><\/p>\n

 <\/p>\n

\u7f8e\u56fd\u7684\u7814\u7a76\u4eba\u5458\u5f00\u53d1\u4e86\u4e00\u79cd\u591a\u529f\u80fd\u7684\u673a\u5668\u5b66\u4e60\u6846\u67b6\uff0c\u4ee5\u5e2e\u52a9\u5bfb\u627e\u65b0\u6750\u6599\u3002\u8fd1\u671f\uff0c\u5728\u7f8e\u56fd\u897f\u5317\u5927\u5b66<\/strong>Christopher Wolverton<\/strong>\u7b49<\/strong>\u4eba\u7684\u5e26\u9886\u4e0b\uff0c\u7814\u7a76\u4eba\u5458\u4f7f\u7528\u5229\u7528\u5df2\u77e5\u6750\u6599\u6570\u636e\u8bad\u7ec3\u7684\u673a\u5668\u5b66\u4e60\u6280\u672f\uff0c\u751f\u6210\u4e86\u9884\u6d4b\u65b0\u6750\u6599\u7279\u5b9a\u5c5e\u6027\u7684\u6a21\u578b\u3002\u4ed6\u4eec\u901a\u8fc7\u7814\u7a76\u4e86\u7528\u4e8e\u5149\u4f0f\u5e94\u7528\u7684\u65b0\u578b\u7ed3\u6676\u5316\u5408\u7269\u4ee5\u53ca\u57fa\u4e8e\u5177\u6709\u5f62\u6210\u73bb\u7483\u7684\u53ef\u80fd\u6027\u7684\u4e09\u5143\u5408\u91d1\u91d1\u5c5e\u73bb\u7483\uff0c\u8bc1\u660e\u4e86\u8be5\u6280\u672f\u7684\u5b9e\u7528\u6027\u3002\u7814\u7a76\u8868\u660e\uff0c\u4f18\u5316\u673a\u5668\u5b66\u4e60\u7b97\u6cd5\u548c\u5206\u533a\u8f93\u5165\u6570\u636e\u6765\u53ef\u4ee5\u521b\u5efa\u65b0\u6a21\u578b\uff0c\u4f7f\u5f97\u7279\u5b9a\u53c2\u6570\u7684\u9884\u6d4b\u7cbe\u5ea6\u8fbe\u5230\u6700\u5927\u5316\u3002\u73b0\u5728\u8be5\u6280\u672f\u5c06\u6709\u671b\u4f9b\u7814\u7a76\u4eba\u5458\u5229\u7528\u5927\u578b\u6750\u6599\u6570\u636e\u5e93\uff0c\u4ece\u800c\u81ea\u52a8\u5316\u548c\u52a0\u901f\u641c\u7d22\u65b0\u7684\u529f\u80fd\u6750\u6599\u3002<\/p>\n

\u6587\u732e\u94fe\u63a5\uff1aA general-purpose machine learning framework for predicting properties of inorganic materials <\/a>(npj Computational Materials\uff0c2018\uff0cDOI\uff1a10.1038\/npjcompumats.2016.28)<\/p>\n

2. \u539f\u5b50\u95f4\u52bf\u9884\u6d4b\u9506\u7684\u76f8\u53d8<\/strong><\/p>\n

\"\"<\/p>\n

\u56fe<\/strong>2 <\/strong>\u7814\u7a76\u63d0\u51fa\u7684\u81ea\u52a8\u68c0\u6d4b\u65b9\u6cd5\u7684\u793a\u610f\u56fe<\/strong><\/p>\n

 <\/p>\n

\u673a\u5668\u5b66\u4e60\u53d1\u73b0\u53ef\u4ee5\u901a\u8fc7\u9506\u7684\u65b0\u7684\u539f\u5b50\u95f4\u52bf\u80fd\u6765\u9884\u6d4b\u76f8\u53d8\u3002\u8fd1\u65e5\uff0c\u7f8e\u56fd\u6d1b\u65af\u963f\u62c9\u83ab\u65af\u56fd\u5bb6\u5b9e\u9a8c\u5ba4<\/strong>Turab Lookman<\/strong>\u7b49\u4eba<\/strong>\u901a\u8fc7\u4f7f\u7528\u9ad8\u65af\u578b\u673a\u5668\u5b66\u4e60\u65b9\u6cd5\u6765\u9884\u6d4b\u9506\u4e2d\u76f8\u53d8\u7684\u539f\u5b50\u95f4\u52bf\u3002\u4ed6\u4eec\u901a\u8fc7\u5c40\u90e8\u539f\u5b50\u73af\u5883\u7684\u53d8\u5316\u6765\u8868\u8ff0\u6bcf\u79cd\u539f\u5b50\u80fd\u91cf\u8d21\u732e\uff0c\u4f8b\u5982\u952e\u957f\u3001\u5f62\u72b6\u548c\u4f53\u79ef\u3002\u7531\u6b64\u4ea7\u751f\u7684\u673a\u5668\u5b66\u4e60\u6210\u529f\u63cf\u8ff0\u4e86\u7eaf\u9506\u7684\u7269\u7406\u7279\u6027\u3002\u5f53\u5176\u7528\u4e8e\u5206\u5b50\u52a8\u529b\u5b66\u6a21\u62df\u65f6\uff0c\u5b83\u9884\u6d4b\u4e86\u9506\u76f8\u56fe\u662f\u6e29\u5ea6\u548c\u538b\u529b\u7684\u51fd\u6570\uff0c\u4e0e\u5148\u524d\u7684\u5b9e\u9a8c\u548c\u6a21\u62df\u4e00\u81f4\u3002\u6b64\u7814\u7a76\u8868\u660e\uff0c\u5728\u76f8\u53d8\u7cfb\u7edf\u4e2d\u5f00\u53d1\u5b66\u4e60\u7684\u539f\u5b50\u95f4\u52bf\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u66f4\u597d\u5730\u6a21\u62df\u590d\u6742\u7684\u7cfb\u7edf\u3002<\/p>\n

\u6587\u732e\u94fe\u63a5\uff1aDeveloping an interatomic potential for martensitic phase transformations in zirconium by machine learning <\/a>(npj Computational Materials\uff0c2018\uff0cDOI: 10.1038\/s41524-018-0103-x\uff09<\/p>\n

3. \u7535\u5b50\u663e\u5fae\u56fe\u50cf\u4e2d\u7684\u81ea\u52a8\u7f3a\u9677\u5206\u6790<\/strong><\/p>\n

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

\u56fe<\/strong>3 <\/strong>\u63d0\u51fa\u7684\u81ea\u52a8\u68c0\u6d4b\u65b9\u6cd5\u7684\u793a\u610f\u6d41\u7a0b\u56fe<\/strong><\/p>\n

 <\/p>\n

\u7535\u5b50\u663e\u5fae\u955c\u548c\u7f3a\u9677\u5206\u6790\u662f\u6750\u6599\u79d1\u5b66\u7684\u57fa\u77f3\uff0c\u56e0\u4e3a\u5b83\u4eec\u63d0\u4f9b\u4e86\u5bf9\u5404\u79cd\u6750\u6599\u548c\u6750\u6599\u7cfb\u7edf\u7684\u5fae\u89c2\u7ed3\u6784\u548c\u6027\u80fd\u7684\u8be6\u7ec6\u89c1\u89e3\u3002\u5982\u679c\u4e3a\u7535\u5b50\u663e\u5fae\u955c\u4e2d\u7684\u81ea\u52a8\u7f3a\u9677\u8bc6\u522b\u548c\u5206\u7c7b\u5efa\u7acb\u4e00\u4e2a\u5f3a\u5927\u800c\u7075\u6d3b\u7684\u5e73\u53f0\uff0c\u5c06\u53ef\u4ee5\u5728\u8bb0\u5f55\u56fe\u50cf\u540e\u751a\u81f3\u5728\u56fe\u50cf\u91c7\u96c6\u8fc7\u7a0b\u4e2d\u66f4\u5feb\u5730\u5b8c\u6210\u5206\u6790\u3002\u7136\u800c\uff0c\u9700\u8981\u5927\u91cf\u56fe\u50cf\u6765\u63d0\u53d6\u7edf\u8ba1\u4e0a\u663e\u7740\u7684\u4fe1\u606f\uff0c\u800c\u8bc6\u522b\u76ee\u524d\u4ecd\u7136\u662f\u624b\u52a8\u5b8c\u6210\u7684\uff0c\u8fd9\u4e0d\u4ec5\u8017\u65f6\u800c\u4e14\u4f1a\u5b58\u5728\u4e0d\u4e00\u81f4\u7684\u60c5\u51b5\u3002\u6700\u8fd1\uff0c\u7f8e\u56fd\u5a01\u65af\u5eb7\u661f\u5927\u5b66\u9ea6\u8fea\u900a\u5206\u6821<\/strong>Dane Morgan<\/strong>\u7b49\u4eba<\/strong>\u548c\u7f8e\u56fd\u6a61\u6811\u5cad\u56fd\u5bb6\u5b9e\u9a8c\u5ba4\u7684\u56e2\u961f\u901a\u8fc7\u5c06\u673a\u5668\u5b66\u4e60\u3001\u8ba1\u7b97\u673a\u89c6\u89c9\u548c\u56fe\u50cf\u5206\u6790\u6280\u672f\u76f8\u7ed3\u5408\uff0c\u83b7\u5f97\u4e86\u6709\u5173\u7f3a\u9677\u5c3a\u5bf8\u548c\u7c7b\u578b\u7684\u4fe1\u606f\u3002\u76ee\u524d\uff0c\u8be5\u7a0b\u5e8f\u7684\u6027\u80fd\u4e0e\u8d28\u91cf\u65b9\u9762\u7684\u4eba\u5de5\u5206\u6790\u4e00\u81f4\uff0c\u5bf9\u5176\u8fdb\u4e00\u6b65\u6539\u8fdb\u53ef\u4ee5\u8fdb\u884c\u5927\u6570\u636e\u96c6\u7684\u5b9e\u65f6\u5206\u6790\u3002<\/p>\n

\u6587\u732e\u94fe\u63a5\uff1aAutomated defect analysis in electron microscopic images<\/a> (npj Computational Materials\uff0c2018\uff0cDOI: 10.1038\/s41524-018-0093-8\uff09<\/p>\n

4. \u901a\u8fc7\u673a\u5668\u5b66\u4e60\u9884\u6d4b\u6709\u673a\u592a\u9633\u80fd\u7535\u6c60\u7684\u6548\u7387<\/strong><\/p>\n

\"\"<\/p>\n

 <\/p>\n

\u56fe<\/strong>4 FF<\/strong>\u548c<\/strong>PCE<\/strong>\u4e0e<\/strong>\u0394Ha<\/sub><\/strong>\u548c<\/strong>\u0394Lb<\/sub><\/strong>\u7684\u76f8\u5173\u6027\u3002<\/strong>\u0394H<\/strong>\u662f<\/strong>HOMO<\/strong>\u548c<\/strong>HOMO-1<\/strong>\u4e4b\u95f4\u7684\u80fd\u91cf\u5dee\u5f02\uff0c<\/strong>\u0394L<\/strong>\u662f\u7ed9\u4f53\u5206\u5b50\u7684<\/strong>LUMO+1<\/strong>\u548c<\/strong>LUMO<\/strong>\u4e4b\u95f4\u7684\u80fd\u91cf\u5dee\u5f02\u3002<\/strong><\/p>\n

\u4e3a\u4e86\u8bbe\u8ba1\u6709\u673a\u5149\u4f0f\uff08OPV\uff09\u7684\u6709\u6548\u6750\u6599\uff0c\u5fc5\u987b\u786e\u5b9a\u63a7\u5236\u5176\u5c5e\u6027\u7684\u6700\u5927\u6570\u91cf\u7684\u53c2\u6570\uff0c\u5e76\u4f7f\u7528\u8fd9\u4e9b\u53c2\u6570\uff08\u79f0\u4e3a\u63cf\u8ff0\u7b26\uff09\u5efa\u7acb\u6a21\u578b\uff0c\u4ee5\u9884\u6d4b\u529f\u7387\u8f6c\u6362\u6548\u7387\uff08PCE\uff09\u3002\u8fd1\u65e5\uff0c\u5357\u4eac\u5927\u5b66\u9a6c\u6d77\u6ce2\u4e0e\u82f1\u56fd\u5229\u7269\u6d66\u5927\u5b66<\/strong>Alessandro Troisi<\/strong>\u7b49\u7814\u7a76\u4eba\u5458<\/strong>\u901a\u8fc7\u6784\u5efa280\u4e2a\u5c0f\u5206\u5b50OPV\u7cfb\u7edf\u7684\u6570\u636e\u96c6\uff0c\u53d1\u73b0\u4e86\u5bf9\u4e8e\u6240\u6709\u9ad8\u6027\u80fd\u88c5\u7f6e\uff0c\u4f9b\u4f53\u5206\u5b50\u7684\u524d\u7ebf\u5206\u5b50\u8f68\u9053\u51e0\u4e4e\u9000\u5316\u3002\u5728\u8fd9\u79cd\u60c5\u51b5\u4e0b\uff0c\u8f68\u9053\u9664\u4e86\u6700\u9ad8\u5360\u636e\u5206\u5b50\u8f68\u9053\uff08HOMO\uff09\u548c\u6700\u4f4e\u7a7a\u5206\u5b50\u8f68\u9053\uff08LUMO\uff09\u53c2\u4e0e\u6fc0\u5b50\u5f62\u6210\u3001\u6fc0\u5b50\u89e3\u79bb\u548c\u7a7a\u7a74\u4f20\u8f93\u8fc7\u7a0b\uff0c\u4ece\u800c\u5f71\u54cdOPV\u7684\u5b8f\u89c2\u6027\u8d28\u3002\u901a\u8fc7\u4f7f\u7528\u673a\u5668\u5b66\u4e60\u65b9\u6cd5\uff0c\u4f7f\u7528\u6709\u673a\u6750\u6599\u768413\u4e2a\u91cd\u8981\u5fae\u89c2\u7279\u6027\u4f5c\u4e3a\u63cf\u8ff0\u7b26\uff0c\u5efa\u7acb\u9884\u6d4bPCE\u7684\u6a21\u578b\u3002\u68af\u5ea6\u589e\u5f3a\u6a21\u578b\u8868\u660e\u5b83\u53ef\u4ee5\u5e94\u7528\u4e8e\u9ad8\u901a\u91cf\u865a\u62df\u7b5b\u9009\u6f5c\u5728\u7684\u65b0\u4f9b\u4f53\u5206\u5b50\uff0c\u4ece\u800c\u5e94\u7528\u4e8e\u9ad8\u6548\u7684OPV\u3002<\/p>\n

\u6587\u732e\u94fe\u63a5\uff1a Toward Predicting Efficiency of Organic Solar Cells via Machine Learning and Improved Descriptors <\/a>(Advanced Energy Materials\uff0c2018\uff0cDOI\uff1a10.1002\/aenm.201801032\uff09<\/p>\n

5. \u5316\u5408\u7269\u7a7a\u95f4\u4e2d\u7684\u91cf\u5b50\u673a\u5668\u5b66\u4e60<\/strong><\/p>\n

\"\"<\/p>\n

\u56fe<\/strong>5 <\/strong>\u57fa\u4e8e\u91cf\u5b50\u529b\u5b66\u901a\u8fc7\u673a\u5668\u5b66\u4e60\u589e\u5f3a\u5bf9\u6027\u8d28\u7684\u7406\u89e3<\/strong><\/p>\n

\u5230\u76ee\u524d\u4e3a\u6b62\uff0c\u4eba\u5de5\u667a\u80fd\u7684\u5e94\u7528\uff0c\u6216\u8005\u66f4\u5177\u4f53\u5730\u8bf4\u662f\u4e25\u683c\u7684\u7edf\u8ba1\u5206\u6790\u548c\u901a\u7528\u6a21\u578b\u7684\u6784\u5efa\uff0c\u5df2\u7ecf\u6210\u4e3a\u73b0\u4ee3\u6280\u672f\u7684\u666e\u904d\u7ec4\u6210\u90e8\u5206\u3002\u901a\u5e38\u63d0\u5230\u7684\u5305\u62ec\u6c7d\u8f66\u3001\u98de\u673a\u6216\u673a\u5668\u4eba\u7684\u81ea\u52a8\u63a7\u5236\uff0c\u6d88\u8d39\u8005\u548c\u5e7f\u544a\u653e\u7f6e\u7684\u5a92\u4f53\u5185\u5bb9\u5efa\u8bae\uff0c\u6295\u8d44\u7ec4\u5408\u548c\u80a1\u7968\u7684\uff08\u9ad8\u9891\uff09\u4ea4\u6613\uff0c\u63a7\u5236\u5047\u80a2\u7684\u5916\u9aa8\u9abc\u8bbe\u5907\u7b49\u5747\u53ef\u4ee5\u5229\u7528\u5176\u66f4\u597d\u5730\u53d1\u6325\u4f5c\u7528\u3002\u745e\u58eb\u5df4\u585e\u5c14\u5927\u5b66<\/strong>O. Anatole von Lilienfeld<\/strong>\u6559\u6388<\/strong>\u63d0\u51fa\uff0c\u673a\u5668\u5b66\u4e60\u65b9\u6cd5\u53ef\u4ee5\u63a8\u65ad\u8fd1\u4f3c\u89e3\uff0c\u901a\u8fc7\u63d2\u5165\u5148\u524d\u83b7\u5f97\u7684\u5206\u5b50\u548c\u6750\u6599\u7684\u5c5e\u6027\u6570\u636e\u96c6\uff0c\u800c\u4e0d\u662f\u5728\u6570\u503c\u4e0a\u6c42\u89e3\u8ba1\u7b97\u8981\u6c42\u7684\u91cf\u5b50\u6216\u7edf\u8ba1\u529b\u5b66\u65b9\u7a0b\u3002\u8be5\u7814\u7a76\u9002\u7528\u4e8e\u91cf\u5b50\u673a\u5668\u5b66\u4e60\uff0c\u662f\u4e00\u79cd\u53ef\u5e7f\u6cdb\u5e94\u7528\u4e8e\u91cf\u5b50\u5316\u5b66\u95ee\u9898\u7684\u5f52\u7eb3\u6027\u5206\u5b50\u5efa\u6a21\u65b9\u6cd5\u3002<\/p>\n

\u6587\u732e\u94fe\u63a5\uff1a Quantum Machine Learning in Chemical Compound Space <\/a>(Angewandte Chemie\uff0c2018\uff0cDOI\uff1a10.1002\/anie.201709686\uff09<\/p>\n


\n 6. \u5173\u8054\u7684\u91d1\u5c5e<\/strong>Pb\/Si(111)<\/strong>\u5355\u5c42\u7535\u8377<\/strong>–<\/strong>\u5bc6\u5ea6\u6ce2\u76f8\u4e2d\u7684\u624b\u6027\u65cb\u8f6c\u7ed3\u6784<\/strong><\/p>\n

\"\"<\/p>\n

\u56fe<\/strong>6 <\/strong>\u8be5\u5de5\u4f5c\u4e2d\u4f7f\u7528\u673a\u5668\u5b66\u4e60\u6a21\u578b\u7684\u8fc7\u7a0b\u793a\u610f\u56fe<\/strong><\/p>\n

 <\/p>\n

\u6563\u88c5\u91d1\u5c5e\u73bb\u7483\uff08BMG\uff09\u662f\u4e00\u7c7b\u72ec\u7279\u7684\u6750\u6599\uff0c\u7531\u4e8e\u5176\u5f15\u4eba\u7684\u7269\u7406\u7279\u6027\uff0c\u76ee\u524d\u5df2\u7ecf\u83b7\u5f97\u4e86\u5e7f\u6cdb\u7684\u5e94\u7528\u3002\u800c\u5236\u7ea6\u4e86\u8fd9\u4e9b\u6750\u6599\u5927\u89c4\u6a21\u4f7f\u7528\u7684\u4e00\u4e2a\u9650\u5236\u662f\u7f3a\u4e4f\u53ef\u9884\u6d4b\u7684\u5de5\u5177\u6765\u5206\u6790\u5408\u91d1\u6210\u5206\u4e0e\u7406\u60f3\u6027\u80fd\u4e4b\u95f4\u7684\u5173\u7cfb\u3002\u4e3a\u4e86\u89e3\u51b3\u8fd9\u4e2a\u95ee\u9898\uff0c\u8fd1\u65e5\uff0c\u7f8e\u56fd\u897f\u5317\u5927\u5b66<\/strong>Chris Wolverton<\/strong>\u7b49\u7814\u7a76\u4eba\u5458<\/strong>\u5f00\u53d1\u4e86\u4e00\u4e2a\u4f7f\u7528\u673a\u5668\u5b66\u4e60\uff08ML\uff09\u6a21\u578b\u8bbe\u8ba1\u91d1\u5c5e\u73bb\u7483\u7684\u6846\u67b6\uff0c\u8be5\u6a21\u578b\u9884\u6d4bBMG\u7ec4\u5408\u7269\u7684\u4e09\u4e2a\u5173\u952e\u7279\u6027\uff1a\u5b58\u5728\u4e8e\u975e\u6676\u6001\u7684\u80fd\u529b\u3001\u4e34\u754c\u94f8\u9020\u76f4\u5f84\u548c\u8fc7\u51b7\u6db2\u4f53\u8303\u56f4\u3002\u8be5\u6a21\u578b\u4ec5\u4f7f\u7528\u5408\u91d1\u7684\u6210\u5206\u4f5c\u4e3a\u8f93\u5165\uff0c\u5e76\u4e14\u662f\u521b\u5efa\u4e8e\u7531\u6570\u5341\u7bc7\u8bba\u6587\u548c\u624b\u518c\u7ec4\u6210\u76848000\u591a\u4e2a\u91d1\u5c5e\u73bb\u7483\u5b9e\u9a8c\u7684\u6570\u636e\u5e93\u3002\u4ed6\u4eec\u4f7f\u7528\u8fd9\u4e9bML\u6a21\u578b\u6765\u4f18\u5316\u73b0\u6709\u5546\u4e1a\u5408\u91d1\u7684\u6027\u80fd\uff0c\u5e76\u4e14\u901a\u8fc7\u5b9e\u9a8c\u53d1\u73b0\uff0c\u8fd9\u51e0\u79cdML\u9884\u6d4b\u7ec4\u5408\u7269\u53ef\u4ee5\u5728\u4ed6\u4eec\u7684\u4e24\u4e2a\u8bbe\u8ba1\u53d8\u91cf\u4e4b\u4e00\u4e2d\u5f62\u6210\u73bb\u7483\u5e76\u8d85\u8fc7\u73b0\u6709\u5408\u91d1\u3002<\/p>\n

\u6587\u732e\u94fe\u63a5\uff1a A machine learning approach for engineering bulk metallic glass alloys <\/a>(Acta Materialia\uff0c2018\uff0cDOI\uff1a10.1016\/j.actamat.2018.08.002\uff09<\/p>\n

7. \u5229\u7528\u673a\u5668\u5b66\u4e60\u6a21\u578b\u5bf9\u786c\u78c1\u76f8\u6210\u5206\u4f18\u5316<\/strong><\/p>\n

\"\"<\/p>\n

\u56fe<\/strong>7 <\/strong>\u6240\u9009\u5316\u5408\u7269\u63cf\u8ff0\u7b26\u7684\u56fe\u793a<\/strong><\/p>\n

\u00a0<\/strong>\u673a\u5668\u5b66\u4e60\uff08ML\uff09\u5728\u65b0\u6750\u6599\u7684\u53d1\u73b0\u548c\u8bbe\u8ba1\u4e2d\u53d1\u6325\u7740\u8d8a\u6765\u8d8a\u91cd\u8981\u7684\u4f5c\u7528\u3002\u5fb7\u56fd\u5f17\u52b3\u6069\u970d\u592b\u6750\u6599\u529b\u5b66\u7814\u7a76\u6240<\/strong>Johannes J. M\u00f6ller<\/strong>\u7b49\u7814\u7a76\u4eba\u5458<\/strong>\u5c55\u793a\u4e86\u4f7f\u7528\u786c\u78c1\u76f8\u4f5c\u4e3a\u89e3\u91ca\u8bf4\u660eML\u5728\u6750\u6599\u7814\u7a76\u65b9\u9762\u7684\u6f5c\u529b\u3002\u4ed6\u4eec\u6784\u5efa\u4e86\u57fa\u4e8e\u5185\u6838\u7684ML\u6a21\u578b\uff0c\u4ee5\u9884\u6d4b\u65b0\u6c38\u78c1\u4f53\u7684\u6700\u4f73\u5316\u5b66\u6210\u5206\uff0c\u8fd9\u662f\u8bb8\u591a\u7eff\u8272\u80fd\u6e90\u6280\u672f\u7684\u5173\u952e\u7ec4\u6210\u90e8\u5206\u3002\u7528\u4e8e\u8bad\u7ec3\u548c\u6d4b\u8bd5ML\u6a21\u578b\u7684\u78c1\u6027\u6570\u636e\u662f\u4ece\u57fa\u4e8e\u5bc6\u5ea6\u6cdb\u51fd\u7406\u8bba\u8ba1\u7b97\u7684\u7ec4\u5408\u9ad8\u901a\u91cf\u7b5b\u9009\u4e2d\u83b7\u5f97\u7684\u3002\u4ed6\u4eec\u76f4\u63a5\u9009\u62e9\u63cf\u8ff0\u4e86\u4e0d\u540c\u7684\u6784\u578b\uff0c\u968f\u540e\u4f7f\u7528ML\u6a21\u578b\u8fdb\u884c\u6210\u5206\u4f18\u5316\uff0c\u4ece\u800c\u9884\u6d4b\u5177\u6709\u7c7b\u4f3c\u5185\u5728\u786c\u78c1\u7279\u6027\u4f46\u6570\u91cf\u8f83\u5c11\u7684Nd2<\/sub>Fe14<\/sub>B\u7b49\u91cd\u8981\u7684\u3001\u6700\u5148\u8fdb\u78c1\u6027\u6750\u6599\u7684\u7a00\u571f\u5143\u7d20\u66ff\u4ee3\u54c1\u3002<\/p>\n

\u6587\u732e\u94fe\u63a5\uff1a Compositional optimization of hard-magnetic phases with machine-learning models <\/a>(Acta Materialia\uff0c2018\uff0cDOI\uff1a10.1016\/j.actamat.2018.03.051\uff09<\/p>\n

8. \u4e24\u6b65\u673a\u5668\u5b66\u4e60\u6307\u5bfc\u9ad8\u6e29\u94c1\u7535\u9499\u949b\u77ff\u7684\u5b9e\u9a8c\u7814\u7a76<\/strong><\/p>\n

\"\"<\/p>\n

\u56fe<\/strong>8 <\/strong>\u5bfb\u627e\u9ad8\u6e29\u94c1\u7535\u9499\u949b\u77ff\u7684\u6750\u6599\u8bbe\u8ba1\u6311\u6218<\/strong><\/p>\n

\u00a0<\/strong><\/p>\n

\u7f8e\u56fd<\/strong>\u6d1b\u65af\u963f\u62c9\u83ab\u65af\u56fd\u5bb6\u5b9e\u9a8c\u5ba4<\/strong>Turab Lookman<\/strong>\u3001\u7f8e\u56fd\u51ef\u65af\u897f\u50a8\u5927\u5b66<\/strong>Alp Sehirlioglu<\/strong>\u4e0e\u7f8e\u56fd\u5f17\u5409\u5c3c\u4e9a\u5927\u5b66<\/strong>Prasanna V. Balachandran<\/strong>\u7b49\u7814\u7a76\u4eba\u5458<\/strong>\u5c55\u793a\u4e86\u4e00\u4e2a\u4e24\u6b65\u673a\u5668\u5b66\u4e60\u7684\u65b9\u6cd5\uff0c\u4ee5\u6307\u5bfc\u5b9e\u9a8c\u5bfb\u627e\u5177\u6709\u9ad8\u94c1\u7535\u5c45\u91cc\u6e29\u5ea6\u7684xBi[Me‘<\/sup>y<\/sub>Me”<\/sup>(1-y)<\/sub>]O3<\/sub>-(1-x)PbTiO3<\/sub>\u57fa\u9499\u949b\u77ff\u3002\u8fd9\u4e9b\u6d89\u53ca\u5206\u7c7b\u7684\u5b66\u4e60\u6765\u7b5b\u9009\u9499\u949b\u77ff\u7ed3\u6784\u4e2d\u7684\u6210\u5206\uff0c\u5e76\u4e14\u56de\u5f52\u4e0e\u4e3b\u52a8\u5b66\u4e60\u76f8\u7ed3\u5408\u4ee5\u8bc6\u522b\u6f5c\u5728\u7684\u9499\u949b\u77ff\uff0c\u7528\u4e8e\u5408\u6210\u548c\u4fe1\u606f\u7684\u53cd\u9988\u3002\u8be5\u95ee\u9898\u662f\u5177\u6709\u6311\u6218\u6027\u7684\uff0c\u56e0\u4e3a\u641c\u7d22\u7a7a\u95f4\u5f88\u5927\uff0c\u8de8\u8d8a\u7ea661500\u4e2a\u7ec4\u5408\uff0c\u53ea\u6709167\u4e2a\u662f\u901a\u8fc7\u5b9e\u9a8c\u7814\u7a76\u53d1\u73b0\u7684\u3002\u6b64\u5916\uff0c\u5e76\u975e\u6bcf\u79cd\u7ec4\u5408\u7269\u90fd\u53ef\u4ee5\u5728\u9499\u949b\u77ff\u76f8\u4e2d\u5408\u6210\u3002\u5728\u8fd9\u9879\u5de5\u4f5c\u4e2d\uff0c\u4ed6\u4eec\u9884\u6d4bx\u3001y\u3001Me’\u548cMe”\u4f7f\u5f97\u6240\u5f97\u7ec4\u5408\u7269\u5177\u6709\u9ad8\u5c45\u91cc\u6e29\u5ea6\u5e76\u4e14\u5728\u9499\u949b\u77ff\u7ed3\u6784\u4e2d\u5f62\u6210\u3002\u7136\u540e\u901a\u8fc7\u4e3b\u52a8\u5b66\u4e60\u6210\u529f\u548c\u5931\u8d25\u7684\u5b9e\u9a8c\u7ed3\u679c\uff0c\u5faa\u73af\u8fed\u4ee3\u5730\u6539\u8fdb\u673a\u5668\u5b66\u4e60\u6a21\u578b\u3002\u8be5\u65b9\u6cd5\u5728\u5408\u6210\u7684\u5341\u79cd\u7ec4\u5408\u7269\u4e2d\u53d1\u73b0\u516d\u79cd\u9499\u949b\u77ff\uff0c\u5305\u62ec\u4e09\u79cd\u5148\u524d\u672a\u5f00\u53d1\u7684{Me’Me”}\u5bf9\uff0c\u5176\u4e2d0.2Bi\uff08Fe0.12<\/sub>Co0.88<\/sub>\uff09O3<\/sub>-0.8PbTiO3<\/sub>\u663e\u793a\u51fa\u6700\u9ad8\u6d4b\u91cf\u7684\u5c45\u91cc\u6e29\u5ea6\u8fbe898K\u3002<\/p>\n

\u6587\u732e\u94fe\u63a5\uff1aExperimental search for high-temperature ferroelectric perovskites guided by two-step machine learning <\/a>(Nature Communications\uff0c2018\uff0cDOI\uff1a10.1038\/s41467-018-03821-9\uff09<\/p>\n

9. \u673a\u5668\u5b66\u4e60\u5efa\u6a21\u9884\u6d4b\u8d85\u5bfc\u4e34\u754c\u6e29\u5ea6<\/strong><\/p>\n

\"\"<\/p>\n

\u56fe<\/strong>9 <\/strong>\u8d85\u5bfc\u4f53\u6570\u636e\u96c6\u548c\u5206\u7c7b\u6a21\u578b\u7684\u6027\u80fd<\/strong><\/p>\n

\u5f00\u53d1\u673a\u5668\u5b66\u4e60\u65b9\u6848\u4ee5\u9ad8\u7cbe\u5ea6\u5730\u6a21\u62df\u8d85\u8fc712,000\u79cd\u5316\u5408\u7269\u7684\u8d85\u5bfc\u8f6c\u53d8\u6e29\u5ea6\u3002\u8fd1\u65e5\uff0c\u7f8e\u56fd\u9a6c\u91cc\u5170\u5927\u5b66<\/strong>Valentin Stanev<\/strong>\u7b49\u7814\u7a76\u4eba\u5458<\/strong>\uff0c\u5305\u62ec\u6765\u81ea\u675c\u514b\u5927\u5b66<\/strong>\u548cNIST<\/strong>\u7684\u7814\u7a76\u4eba\u5458\uff0c\u5f00\u53d1\u4e86\u51e0\u79cd\u673a\u5668\u5b66\u4e60\u65b9\u6848\uff0c\u7528\u4e8e\u6a21\u62df\u8d85\u8fc712,000\u79cd\u5df2\u77e5\u8d85\u5bfc\u4f53\u548c\u5019\u9009\u6750\u6599\u7684\u4e34\u754c\u6e29\u5ea6\uff08Tc\uff09\u3002\u4ed6\u4eec\u9996\u5148\u4ec5\u6839\u636e\u5316\u5b66\u6210\u5206\u8bad\u7ec3\u5206\u7c7b\u6a21\u578b\uff0c\u6839\u636e\u5176Tc\u662f\u9ad8\u4e8e\u8fd8\u662f\u4f4e\u4e8e10 K\u5bf9\u5df2\u77e5\u8d85\u5bfc\u4f53\u8fdb\u884c\u5206\u7c7b\u3002\u7136\u540e\uff0c\u4ed6\u4eec\u5f00\u53d1\u56de\u5f52\u6a21\u578b\u6765\u9884\u6d4b\u5404\u79cd\u5316\u5408\u7269\u7684Tc\u503c\u3002\u901a\u8fc7\u5305\u542bAFLOW\u5728\u7ebf\u5b58\u50a8\u5e93\u4e2d\u7684\u6570\u636e\uff0c\u53ef\u4ee5\u8fdb\u4e00\u6b65\u63d0\u9ad8\u8fd9\u4e9b\u6a21\u578b\u7684\u51c6\u786e\u6027\u3002\u4ed6\u4eec\u5c06\u5206\u7c7b\u548c\u56de\u5f52\u6a21\u578b\u7ec4\u5408\u6210\u4e00\u4e2a\u5355\u4e00\u7684\u96c6\u6210\u7ba1\u9053\uff0c\u4ee5\u641c\u7d22\u6574\u4e2a\u65e0\u673a\u6676\u4f53\u7ed3\u6784\u6570\u636e\u5e93\uff0c\u5e76\u9884\u6d4b\u8d85\u8fc730\u4e2a\u65b0\u7684\u5019\u9009\u8d85\u5bfc\u4f53\u3002<\/p>\n

\u6587\u732e\u94fe\u63a5\uff1aMachine learning modeling of superconducting critical temperature<\/a> (npj Computational Materials\uff0c2018\uff0cDOI\uff1a10.1038\/s41524-018-0085-8\uff09<\/p>\n

10. \u4f7f\u7528\u673a\u5668\u5b66\u4e60\u7cbe\u786e\u9884\u6d4b<\/strong>X<\/strong>\u5c04\u7ebf\u8109\u51b2\u7279\u6027<\/strong><\/p>\n

\"\"<\/p>\n

\u56fe<\/strong>10 <\/strong>\u57fa\u4e8e\u673a\u5668\u5b66\u4e60\u7684\u793a\u610f\u56fe<\/strong><\/p>\n

\u81ea\u7531\u7535\u5b50\u6fc0\u5149\u5668\u63d0\u4f9b\u8d85\u77ed\u7684\u9ad8\u4eae\u5ea6X\u5c04\u7ebf\u8f90\u5c04\u8109\u51b2\uff0c\u5bf9\u4e8e\u79d1\u5b66\u7684\u5e7f\u6cdb\u5f71\u54cd\u5177\u6709\u5de8\u5927\u7684\u6f5c\u529b\uff0c\u5e76\u4e14\u662f\u89e3\u5f00\u7269\u8d28\u7ed3\u6784\u52a8\u529b\u5b66\u7684\u5173\u952e\u56e0\u7d20\u3002 \u4e3a\u4e86\u5145\u5206\u5229\u7528\u8fd9\u4e00\u6f5c\u529b\uff0c\u5fc5\u987b\u51c6\u786e\u5730\u4e86\u89e3X\u5c04\u7ebf\u7279\u6027\uff1a\u5f3a\u5ea6\u3001\u5149\u8c31\u548c\u65f6\u95f4\u5206\u5e03\u3002\u7531\u4e8e\u81ea\u7531\u7535\u5b50\u6fc0\u5149\u5668\u7684\u56fa\u6709\u6ce2\u52a8\uff0c\u8fd9\u8981\u6c42\u5bf9\u6bcf\u4e2a\u8109\u51b2\u7684\u7279\u6027\u8fdb\u884c\u5168\u9762\u8868\u5f81\u3002\u867d\u7136\u5b58\u5728\u5bf9\u8fd9\u4e9b\u7279\u6027\u7684\u8bca\u65ad\uff0c\u4f46\u5b83\u4eec\u901a\u5e38\u662f\u5177\u6709\u4fb5\u5bb3\u6027\u7684\uff0c\u5e76\u4e14\u8bb8\u591a\u4e0d\u80fd\u4ee5\u9ad8\u91cd\u590d\u7387\u64cd\u4f5c\u3002\u8fd1\u671f\uff0c\u82f1\u56fd\u5e1d\u56fd\u7406\u5de5\u5b66\u9662<\/strong>A. Sanchez-Gonzalez<\/strong>\u548c<\/strong>J. P. Marangos<\/strong>\u7b49\u7814\u7a76\u4eba\u5458<\/strong>\u63d0\u51fa\u4e86\u4e00\u79cd\u7ed5\u8fc7\u8fd9\u79cd\u9650\u5236\u7684\u6280\u672f\u3002\u4ed6\u4eec\u91c7\u7528\u673a\u5668\u5b66\u4e60\u7b56\u7565\uff0c\u53ef\u4ee5\u901a\u8fc7\u5728\u4e00\u5c0f\u7ec4\u5b8c\u5168\u8bca\u65ad\u7684\u8109\u51b2\u4e0a\u8bad\u7ec3\u6a21\u578b\uff0c\u4ec5\u4f7f\u7528\u6613\u4e8e\u4ee5\u9ad8\u91cd\u590d\u7387\u8bb0\u5f55\u7684\u53c2\u6570\u6765\u51c6\u786e\u9884\u6d4b\u6bcf\u6b21\u5c04\u51fb\u7684X\u5c04\u7ebf\u5c5e\u6027\u3002\u8fd9\u4e3a\u5b8c\u5168\u5b9e\u73b0\u4e0b\u4e00\u4ee3\u9ad8\u91cd\u590d\u7387X\u5c04\u7ebf\u6fc0\u5149\u5668\u6253\u5f00\u4e86\u5927\u95e8\u3002<\/p>\n

\u6587\u732e\u94fe\u63a5\uff1aAccurate prediction of X-ray pulse properties from a free-electron laser using machine learning<\/a> (Nature Communications\uff0c2018\uff0cDOI\uff1a 10.1038\/ncomms15461\uff09<\/p>\n

\u672c\u6587\u7531\u6750\u6599\u4eba\u8ba1\u7b97\u6750\u6599\u7ec4Annay\u4f9b\u7a3f\uff0c\u6750\u6599\u725b\u6574\u7406\u7f16\u8f91\u3002<\/p>\n

\u6b22\u8fce\u5927\u5bb6\u5230\u6750\u6599\u4eba\u5ba3\u4f20\u79d1\u6280\u6210\u679c\u5e76\u5bf9\u6587\u732e\u8fdb\u884c\u6df1\u5165\u89e3\u8bfb\uff0c\u6295\u7a3f\u90ae\u7bb1tougao@cailiaoren.com<\/a>\u3002<\/p>\n

\u6295\u7a3f\u4ee5\u53ca\u5185\u5bb9\u5408\u4f5c\u53ef\u52a0\u7f16\u8f91\u5fae\u4fe1\uff1a<\/strong>cailiaokefu<\/strong><\/p>\n

\u5982\u679c\u60a8\u60f3\u5229\u7528\u7406\u8bba\u8ba1\u7b97\u6765\u5e2e\u52a9\u5b9e\u9a8c\uff0c\u6b22\u8fce\u60a8\u4f7f\u7528\u6750\u6599\u4eba\u8ba1\u7b97\u6a21\u62df\u89e3\u51b3\u65b9\u6848\u3002\u6750\u6599\u4eba\u7ec4\u5efa\u4e86\u4e00\u652f\u6765\u81ea\u5168\u56fd\u77e5\u540d\u9ad8\u6821\u8001\u5e08\u53ca\u4f01\u4e1a\u5de5\u7a0b\u5e08\u7684\u79d1\u6280\u987e\u95ee\u56e2\u961f\uff0c\u4e13\u6ce8\u4e8e\u4e3a\u5927\u5bb6\u89e3\u51b3\u5404\u7c7b\u8ba1\u7b97\u6a21\u62df\u9700\u6c42\u3002\u5982\u679c\u60a8\u6709\u9700\u6c42\uff0c\u6b22\u8fce\u626b\u4ee5\u4e0b\u4e8c\u7ef4\u7801\u63d0\u4ea4\u60a8\u7684\u9700\u6c42\uff0c\u6216\u76f4\u63a5\u8054\u7cfb\u5fae\u4fe1\u5ba2\u670d\uff08\u5fae\u4fe1\u53f7\uff1acailiaoren001\uff09<\/p>\n

\"\"<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

\u6750\u6599\u4eba\u7ee7\u7eed\u63a8\u51fa\u8ba1\u7b97\u6750\u6599\u6210\u679c\u6c47\u7f16\uff08\u6708\u520a\uff09\uff0c\u62a5\u9053\u8ba1\u7b97\u6750\u6599\u76f8\u5173\u91cd\u5927\u6210\u679c\u3002\u672c\u7bc7\u4e3a\u673a\u5668\u5b66\u4e60\u4e13\u520a\u3002 1. \u673a\u5668\u5b66\u4e60\u7528\u4e8e\u9884\u6d4b\u65e0\u673a\u6750\u6599\u7684\u6027\u80fd \u56fe1 Al-Ni-Zr\u4e09\u5143\u533a\u73bb\u7483\u6210…<\/p>\n","protected":false},"author":5415,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2810],"tags":[78,18,97,30,346,244],"class_list":["post-152809","post","type-post","status-publish","format-standard","hentry","category-huizong","tag-photovoltaic","tag-xinnengyuan","tag-computation","tag-chaodao","tag-metal","tag-gaitaikuang"],"_links":{"self":[{"href":"\/\/m.iemloyee.com\/index.php?rest_route=\/wp\/v2\/posts\/152809"}],"collection":[{"href":"\/\/m.iemloyee.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"\/\/m.iemloyee.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"\/\/m.iemloyee.com\/index.php?rest_route=\/wp\/v2\/users\/5415"}],"replies":[{"embeddable":true,"href":"\/\/m.iemloyee.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=152809"}],"version-history":[{"count":6,"href":"\/\/m.iemloyee.com\/index.php?rest_route=\/wp\/v2\/posts\/152809\/revisions"}],"predecessor-version":[{"id":152955,"href":"\/\/m.iemloyee.com\/index.php?rest_route=\/wp\/v2\/posts\/152809\/revisions\/152955"}],"wp:attachment":[{"href":"\/\/m.iemloyee.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=152809"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"\/\/m.iemloyee.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=152809"},{"taxonomy":"post_tag","embeddable":true,"href":"\/\/m.iemloyee.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=152809"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}