?? lin2quad.html
字號:
<html><head> <meta HTTP-EQUIV="Content-Type" CONTENT="text/html;charset=ISO-8859-1"> <title>lin2quad.m</title><link rel="stylesheet" type="text/css" href="../../m-syntax.css"></head><body><code><span class=defun_kw>function</span> <span class=defun_out>quad_model </span>= <span class=defun_name>lin2quad</span>(<span class=defun_in>lin_model</span>)<br><span class=h1>% LIN2QUAD Merges linear rule and quadratic mapping.</span><br><span class=help>% </span><br><span class=help>% <span class=help_field>Synopsis:</span></span><br><span class=help>% quad_model = lin2quad(lin_model)</span><br><span class=help>%</span><br><span class=help>% <span class=help_field>Description:</span></span><br><span class=help>% It recomputes parameters of input linear classifier</span><br><span class=help>% onto parameters of output quadratic classisifier.</span><br><span class=help>% The linear classifier is assumed to be trained on </span><br><span class=help>% the n-dimensional data quadraticaly mapped (see 'help qmap') </span><br><span class=help>% into the (n*(n+3)/2)-dimensional feature space. The linear </span><br><span class=help>% classifier in the feature space appears as the quadratic </span><br><span class=help>% classifier in the original data space.</span><br><span class=help>%</span><br><span class=help>% <span class=help_field>Description:</span></span><br><span class=help>% orig_data = load('vltava');</span><br><span class=help>% map_data = qmap(orig_data);</span><br><span class=help>% lin_model = perceptron(map_data);</span><br><span class=help>% quad_model = lin2quad(lin_model);</span><br><span class=help>% figure; ppatterns(orig_data); </span><br><span class=help>% pboundary(quad_model);</span><br><span class=help>%</span><br><span class=help>% See also </span><br><span class=help>% QUACLASS, QMAP</span><br><span class=help>%</span><br><hr><span class=help1>% <span class=help1_field>Modifications:</span></span><br><span class=help1>% 09-jun-2004, VF</span><br><span class=help1>% 17-may-2004, VF</span><br><br><hr><span class=comment>% allows input model to be cell</span><br>lin_model = c2s( lin_model );<br><br><span class=comment>% check dimension</span><br>[m, nfun] = size( lin_model.W );<br>n = (-3 + sqrt( 9 + 8*m ))/2;<br><span class=keyword>if</span> round(n) ~= n,<br> <span class=error>error</span>(<span class=quotes>'Wrong dimension of input linear classifier.'</span>);<br><span class=keyword>end</span><br><br>quad_model.A = zeros(n,n,nfun);<br>quad_model.B = lin_model.W(1:n,:);<br>quad_model.C = lin_model.b(:)';<br><br><span class=keyword>for</span> k=1:nfun<br><br> cnt = n;<br> <span class=keyword>for</span> i=1:n,<br> <span class=keyword>for</span> j=i:n,<br> cnt = cnt + 1;<br> <span class=keyword>if</span> i == j,<br> quad_model.A(i,j,k) = lin_model.W(cnt,k);<br> <span class=keyword>else</span><br> quad_model.A(i,j,k) = 0.5*lin_model.W(cnt,k);<br> quad_model.A(j,i,k) = 0.5*lin_model.W(cnt,k);<br> <span class=keyword>end</span><br> <span class=keyword>end</span><br> <span class=keyword>end</span><br><span class=keyword>end</span><br><br>quad_model.fun = <span class=quotes>'quadclass'</span>;<br><br><span class=jump>return</span>;<br><span class=comment>%EOF</span><br></code>?? 快捷鍵說明
復制代碼
Ctrl + C
搜索代碼
Ctrl + F
全屏模式
F11
切換主題
Ctrl + Shift + D
顯示快捷鍵
?
增大字號
Ctrl + =
減小字號
Ctrl + -