?? node20.html
字號:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2//EN"><!--Converted with LaTeX2HTML 97.1 (release) (July 13th, 1997) by Nikos Drakos (nikos@cbl.leeds.ac.uk), CBLU, University of Leeds* revised and updated by: Marcus Hennecke, Ross Moore, Herb Swan* with significant contributions from: Jens Lippman, Marek Rouchal, Martin Wilck and others --><HTML><HEAD><TITLE>5.4.6 Growing Neural Gas, Growing NeuralGas with Utility</TITLE><META NAME="description" CONTENT="5.4.6 Growing Neural Gas, Growing NeuralGas with Utility"><META NAME="keywords" CONTENT="DemoGNG"><META NAME="resource-type" CONTENT="document"><META NAME="distribution" CONTENT="global"><META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso_8859_1"><LINK REL="STYLESHEET" HREF="DemoGNG.css"><LINK REL="next" HREF="node21.html"><LINK REL="previous" HREF="node19.html"><LINK REL="up" HREF="node14.html"><LINK REL="next" HREF="node21.html"></HEAD><BODY ><!--Navigation Panel--><A NAME="tex2html301" HREF="node21.html"><IMG WIDTH="37" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="next" SRC="http://www.neuroinformatik.ruhr-uni-bochum.de/icons/next_motif.gif"></A> <A NAME="tex2html298" HREF="node14.html"><IMG WIDTH="26" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="up" SRC="http://www.neuroinformatik.ruhr-uni-bochum.de/icons/up_motif.gif"></A> <A NAME="tex2html292" HREF="node19.html"><IMG WIDTH="63" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="previous" SRC="http://www.neuroinformatik.ruhr-uni-bochum.de/icons/previous_motif.gif"></A> <A NAME="tex2html300" HREF="node1.html"><IMG WIDTH="65" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="contents" SRC="http://www.neuroinformatik.ruhr-uni-bochum.de/icons/contents_motif.gif"></A> <BR><B> Next:</B> <A NAME="tex2html302" HREF="node21.html">5.4.7 Self-Organizing Map</A><B> Up:</B> <A NAME="tex2html299" HREF="node14.html">5.4 Model Specific Options</A><B> Previous:</B> <A NAME="tex2html293" HREF="node19.html">5.4.5 Neural Gas with</A><BR><BR><!--End of Navigation Panel--><A NAME="tex2html1" HREF="http://www.neuroinformatik.ruhr-uni-bochum.de/ini/VDM/research/gsn/DemoGNG/GNG_3.html">Growing Neural Gas</A><IMG WIDTH="49" HEIGHT="38" ALIGN="BOTTOM" BORDER="0" SRC="../smallDuke.gif">, <A NAME="tex2html1" HREF="http://www.neuroinformatik.ruhr-uni-bochum.de/ini/VDM/research/gsn/DemoGNG/GNG-U_10.html">Growing NeuralGas with Utility</A><IMG WIDTH="49" HEIGHT="38" ALIGN="BOTTOM" BORDER="0" SRC="../smallDuke.gif"><H3><A NAME="SECTION00074600000000000000">5.4.6 </A></H3><DL><DT><STRONG>No new Nodes</STRONG><DD>No new nodes will be inserted.<DT><STRONG>Utility</STRONG><DD>Switches from GNG to GNG-U and back. The value (<I>k</I>) determinesthe deletion of the unit with the smallest utility <I>U</I><SUB><I>i</I></SUB> (<IMG WIDTH="116" HEIGHT="25" ALIGN="MIDDLE" BORDER="0" SRC="img20.gif" ALT="$i := arg\ min_cU_c$">), if the utility value falls below a certain fraction of the error variable <I>E</I><SUB><I>q</I></SUB>: <I>k</I> < <I>E</I><SUB><I>q</I></SUB>/<I>U</I><SUB><I>i</I></SUB>.<DT><STRONG>Lambda</STRONG><DD>If the number of input signals generated so far is an integer multiple of this value (<IMG WIDTH="12" HEIGHT="14" ALIGN="BOTTOM" BORDER="0" SRC="img21.gif" ALT="$\lambda$">), insert a new node.<DT><STRONG>max. Edge Age</STRONG><DD>Remove edges with an age larger than this value (<I>a</I><SUB><I>max</I></SUB>). If this results in nodes having no emanating edges, remove them as well.<DT><STRONG>Epsilon winner</STRONG><DD>Move the winner node towards the input signal by this fraction of the total distance (<IMG WIDTH="15" HEIGHT="24" ALIGN="MIDDLE" BORDER="0" SRC="img22.gif" ALT="$\epsilon_b$">).<DT><STRONG>Epsilon neighbor</STRONG><DD>Move the neighbors of the winner node towards the input signal by this fraction of the total distance (<IMG WIDTH="17" HEIGHT="24" ALIGN="MIDDLE" BORDER="0" SRC="img23.gif" ALT="$\epsilon_n$">).<DT><STRONG>alpha</STRONG><DD>Decrease the error variables of the nodes neighboring to the newly inserted node by a fraction of this size (<IMG WIDTH="13" HEIGHT="12" ALIGN="BOTTOM" BORDER="0" SRC="img24.gif" ALT="$\alpha$">).<DT><STRONG>beta</STRONG><DD>Decrease the error variables of all nodes by a fraction of this size (<IMG WIDTH="12" HEIGHT="26" ALIGN="MIDDLE" BORDER="0" SRC="img25.gif" ALT="$\beta$">).</DL><HR><!--Navigation Panel--><A NAME="tex2html301" HREF="node21.html"><IMG WIDTH="37" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="next" SRC="http://www.neuroinformatik.ruhr-uni-bochum.de/icons/next_motif.gif"></A> <A NAME="tex2html298" HREF="node14.html"><IMG WIDTH="26" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="up" SRC="http://www.neuroinformatik.ruhr-uni-bochum.de/icons/up_motif.gif"></A> <A NAME="tex2html292" HREF="node19.html"><IMG WIDTH="63" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="previous" SRC="http://www.neuroinformatik.ruhr-uni-bochum.de/icons/previous_motif.gif"></A> <A NAME="tex2html300" HREF="node1.html"><IMG WIDTH="65" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="contents" SRC="http://www.neuroinformatik.ruhr-uni-bochum.de/icons/contents_motif.gif"></A> <BR><B> Next:</B> <A NAME="tex2html302" HREF="node21.html">5.4.7 Self-Organizing Map</A><B> Up:</B> <A NAME="tex2html299" HREF="node14.html">5.4 Model Specific Options</A><B> Previous:</B> <A NAME="tex2html293" HREF="node19.html">5.4.5 Neural Gas with</A><!--End of Navigation Panel--><ADDRESS><I>Hartmut S. Loos</I><BR><I>10/19/1998</I></ADDRESS></BODY></HTML>?? 快捷鍵說明
復(fù)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 + -