constructiveregression.html
来自「数据挖掘方面最新软件」· HTML 代码 · 共 832 行 · 第 1/3 页
HTML
832 行
<TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>protected void</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../../../../com/rapidminer/operator/learner/functions/kernel/rvm/ConstructiveRegression.html#deleteBasis(int)">deleteBasis</A></B>(int selectedBasis)</CODE><BR> Delete a basis function from the model.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>protected void</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../../../../com/rapidminer/operator/learner/functions/kernel/rvm/ConstructiveRegression.html#includeBasis(int)">includeBasis</A></B>(int selectedBasis)</CODE><BR> Include a basis function into the model.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>protected double</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../../../../com/rapidminer/operator/learner/functions/kernel/rvm/ConstructiveRegression.html#innerProduct(double[], double[])">innerProduct</A></B>(double[] x, double[] y)</CODE><BR> Return the inner product of x and y (x.length == y.length assumed)</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE> <A HREF="../../../../../../../com/rapidminer/operator/learner/functions/kernel/rvm/Model.html" title="class in com.rapidminer.operator.learner.functions.kernel.rvm">Model</A></CODE></FONT></TD><TD><CODE><B><A HREF="../../../../../../../com/rapidminer/operator/learner/functions/kernel/rvm/ConstructiveRegression.html#learn()">learn</A></B>()</CODE><BR> The hard work is done here</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>protected void</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../../../../com/rapidminer/operator/learner/functions/kernel/rvm/ConstructiveRegression.html#prune(java.util.LinkedList)">prune</A></B>(java.util.LinkedList<java.lang.Integer> basisSet)</CODE><BR> Create pruned versions of all important matrices / vectors so that only rows / columns matching the indices in basisSet are kept.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>protected void</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../../../../com/rapidminer/operator/learner/functions/kernel/rvm/ConstructiveRegression.html#reestimateAlpha(int)">reestimateAlpha</A></B>(int selectedBasis)</CODE><BR> Reestimate alpha by setting it to the value which maximizes the marginal likelihood: alpha_i = s^2_i / (q^2_i - s_i)</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE> java.lang.String</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../../../../com/rapidminer/operator/learner/functions/kernel/rvm/ConstructiveRegression.html#toString()">toString</A></B>()</CODE><BR> Identify the RVM</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>protected void</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../../../../com/rapidminer/operator/learner/functions/kernel/rvm/ConstructiveRegression.html#updateBeta()">updateBeta</A></B>()</CODE><BR> Update beta (same as for the "normal" regression rvm)</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>protected void</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../../../../com/rapidminer/operator/learner/functions/kernel/rvm/ConstructiveRegression.html#updateCriteriumScalars(int)">updateCriteriumScalars</A></B>(int selectedBasis)</CODE><BR> Compute the scalars s_m, q_m which are part of the criterium for inclusion / deletion of the given basis m: S_m = beta * phi^t_m * phi_m - beta^2 * phi^t_m * PHI * SIGMA * PHI^t * phi_m Q_m = beta * phi^t_m * t - beta^2 * phi^t_m * PHI * SIGMA * PHI^t * t s_m = alpha_m * S_m / (alpha_m - S_m) q_m = alpha_m * Q_m / (alpha_m - S_m)</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>protected void</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../../../../com/rapidminer/operator/learner/functions/kernel/rvm/ConstructiveRegression.html#updateMu()">updateMu</A></B>()</CODE><BR> Update the mean of the weight posterior distribution (mu): mu = beta * SIGMA * PHI^t * t</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>protected void</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../../../../com/rapidminer/operator/learner/functions/kernel/rvm/ConstructiveRegression.html#updateSIGMA()">updateSIGMA</A></B>()</CODE><BR> Update the covariance Matrix of the weight posterior distribution (SIGMA) along with its cholesky factor: SIGMA = (A + beta * PHI^t * PHI)^{-1} SIGMA_chol with SIGMA_chol * SIGMA_chol^t = SIGMA</TD></TR></TABLE> <A NAME="methods_inherited_from_class_com.rapidminer.operator.learner.functions.kernel.rvm.RVMBase"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor"><TH ALIGN="left"><B>Methods inherited from class com.rapidminer.operator.learner.functions.kernel.rvm.<A HREF="../../../../../../../com/rapidminer/operator/learner/functions/kernel/rvm/RVMBase.html" title="class in com.rapidminer.operator.learner.functions.kernel.rvm">RVMBase</A></B></TH></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD><CODE><A HREF="../../../../../../../com/rapidminer/operator/learner/functions/kernel/rvm/RVMBase.html#getModel()">getModel</A></CODE></TD></TR></TABLE> <A NAME="methods_inherited_from_class_java.lang.Object"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor"><TH ALIGN="left"><B>Methods inherited from class java.lang.Object</B></TH></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD><CODE>clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait</CODE></TD></TR></TABLE> <P><!-- ============ FIELD DETAIL =========== --><A NAME="field_detail"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor"><TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2"><B>Field Detail</B></FONT></TH></TR></TABLE><A NAME="x"><!-- --></A><H3>x</H3><PRE>protected double[][] <B>x</B></PRE><DL><DD>Data shared accross various methods<P><DL></DL></DL><HR><A NAME="t"><!-- --></A><H3>t</H3><PRE>protected double[][] <B>t</B></PRE><DL><DL></DL></DL><HR><A NAME="tVector"><!-- --></A><H3>tVector</H3><PRE>protected double[] <B>tVector</B></PRE><DL><DL></DL></DL><HR><A NAME="phi"><!-- --></A><H3>phi</H3><PRE>protected double[][] <B>phi</B></PRE><DL><DL></DL></DL><HR><A NAME="PHI_t"><!-- --></A><H3>PHI_t</H3><PRE>protected Jama.Matrix <B>PHI_t</B></PRE><DL><DL></DL></DL><HR><A NAME="alpha"><!-- --></A><H3>alpha</H3><PRE>protected double[] <B>alpha</B></PRE><DL><DL></DL></DL><HR><A NAME="beta"><!-- --></A><H3>beta</H3><PRE>protected double <B>beta</B></PRE><DL><DL></DL></DL><HR><A NAME="A"><!-- --></A><H3>A</H3><PRE>protected Jama.Matrix <B>A</B></PRE><DL><DL></DL></DL><HR><A NAME="SIGMA"><!-- --></A><H3>SIGMA</H3><PRE>protected Jama.Matrix <B>SIGMA</B></PRE><DL><DL></DL></DL><HR><A NAME="SIGMA_chol"><!-- --></A><H3>SIGMA_chol</H3><PRE>protected Jama.Matrix <B>SIGMA_chol</B></PRE><DL><DL></DL></DL><HR><A NAME="mu"><!-- --></A><H3>mu</H3><PRE>protected Jama.Matrix <B>mu</B></PRE><DL><DL></DL></DL><HR><A NAME="s"><!-- --></A><H3>s</H3><PRE>protected double <B>s</B></PRE><DL><DL></DL></DL><HR><A NAME="q"><!-- --></A><H3>q</H3><PRE>protected double <B>q</B></PRE><DL><DL></DL></DL><HR><A NAME="basisSet"><!-- --></A><H3>basisSet</H3><PRE>protected java.util.LinkedList<java.lang.Integer> <B>basisSet</B></PRE><DL><DL></DL>⌨️ 快捷键说明
复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?