SPA-连续投影算法-教程版.zip_算法_其他

<html xmlns="http://www.w3.org/1999/xhtml"> <head> <meta charset="utf-8"> <meta name="generator" content="pdf2htmlEX"> <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1"> <link rel="stylesheet" href="https://static.pudn.com/base/css/base.min.css"> <link rel="stylesheet" href="https://static.pudn.com/base/css/fancy.min.css"> <link rel="stylesheet" href="https://static.pudn.com/prod/directory_preview_static/627735ab517cd20ea48cd16d/raw.css"> <script src="https://static.pudn.com/base/js/compatibility.min.js"></script> <script src="https://static.pudn.com/base/js/pdf2htmlEX.min.js"></script> <script> try{ pdf2htmlEX.defaultViewer = new pdf2htmlEX.Viewer({}); }catch(e){} </script> <title></title> </head> <body> <div id="sidebar" style="display: none"> <div id="outline"> </div> </div> <div id="pf1" class="pf w0 h0" data-page-no="1"><div class="pc pc1 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://static.pudn.com/prod/directory_preview_static/627735ab517cd20ea48cd16d/bg1.jpg"><div class="c x0 y1 w2 h2"><div class="t m0 x1 h3 y2 ff1 fs0 fc0 sc0 ls0 ws0">1.<span class="ff2">为了快速演示，我在数据中截取了前<span class="_ _0"> </span></span>30<span class="_ _0"> </span><span class="ff2">个特征，你可以自行设定。</span></div><div class="t m0 x1 h3 y3 ff1 fs0 fc0 sc0 ls0 ws0">2.<span class="ff2">运行<span class="_ _0"> </span></span>shujv<span class="_ _1"></span>.m</div><div class="t m0 x1 h3 y4 ff1 fs0 fc0 sc0 ls0 ws0">3.<span class="ff2">打开<span class="_ _0"> </span></span>spa.m <span class="ff2">点击绿色三角下的黑色小三角输入参数</span></div><div class="t m0 x1 h3 y5 ff1 fs0 fc0 sc0 ls0 ws0"> Xcal,ycal:<span class="ff2">你要进行降维的数据</span></div><div class="t m0 x1 h3 y6 ff1 fs0 fc0 sc0 ls0 ws0"> Xval,yval:<span class="ff2">交叉验证的数据，如果不需要交叉验证两个参数为空，如图。</span></div><div class="t m0 x1 h3 y7 ff1 fs0 fc0 sc0 ls0 ws0"> m_min,m_max:<span class="ff2">设定需要降维后的数据维度的范围，即降维后维度最小为<span class="_ _0"> </span></span>m_min<span class="ff2">，最大</span></div><div class="t m0 x2 h3 y8 ff2 fs0 fc0 sc0 ls0 ws0">为<span class="_ _0"> </span><span class="ff1">m_max</span>。</div><div class="t m0 x1 h3 y9 ff1 fs0 fc0 sc0 ls0 ws0"> autoscaling:<span class="ff2">是否自动定量</span>-> 1 (yes) or 0 (no)<span class="_ _2"></span><span class="ff2">。</span></div><div class="t m0 x1 h3 ya ff1 fs0 fc0 sc0 ls0 ws0">4.<span class="ff2">降维结果</span></div><div class="t m0 x1 h3 yb ff1 fs0 fc0 sc0 ls0 ws0"> <span class="_ _2"></span><span class="ff2">左<span class="_ _2"></span>图表<span class="_ _2"></span>示<span class="_ _2"></span>选择<span class="_ _3"> </span></span>8<span class="_ _0"> </span><span class="ff2">个<span class="_ _2"></span>维度<span class="_ _2"></span>时<span class="_ _3"> </span></span>R<span class="_ _4"></span>MSE<span class="_ _0"> </span><span class="ff2">最<span class="_ _2"></span>小，<span class="_ _2"></span>之<span class="_ _2"></span>后虽<span class="_ _2"></span>然<span class="_ _2"></span>维度<span class="_ _2"></span>增加<span class="_ _2"></span>，<span class="_ _2"></span>但<span class="_ _3"> </span></span>RMSE<span class="_ _0"> </span><span class="ff2">降<span class="_ _2"></span>幅很<span class="_ _2"></span>小<span class="_ _2"></span>，类<span class="_ _2"></span>似<span class="_ _2"></span>于</span></div><div class="t m0 x1 h3 yc ff2 fs0 fc0 sc0 ls0 ws0">梯度下降中梯度收敛。</div><div class="t m0 x1 h3 yd ff1 fs0 fc0 sc0 ls0 ws0"> <span class="ff2">右图中红色方框标记标记对应的维度就是我们降维度后最终选择的维度。</span></div></div></div><div class="pi" data-data='{"ctm":[1.611850,0.000000,0.000000,1.611850,0.000000,0.000000]}'></div></div> </body> </html>