demogng-1.2.tex

关于自组织神经网络的一种新结构程序,并包含了其它几种神经网络的程序比较

\documentclass{article}
\usepackage{a4}
%\usepackage{/u/user/loos/TeX/latex2html/texinputs/html}
\usepackage{html}
\usepackage{epsfig}
\usepackage{changebar}

%commands for epsf-files with a width which is a fraction of \textwidth
%
% my epsf (not centered, width set to given fraction of textwidth)
\newcommand{\myepsf}[2]{\epsfxsize#2\textwidth \epsffile{#1}}
% my centered epsf (centered, width set to given fraction of textwidth)
\newcommand{\mycepsf}[2]{\epsfxsize#2\textwidth \centerline{\epsffile{#1}}}
% my centered and boxed epsf
\newcommand{\mycbepsf}[2]{\epsfxsize#2\textwidth \centerline{\fbox{\epsffile{#1}}}}
% my boxed epsf
\newcommand{\mybepsf}[2]{\epsfxsize#2\textwidth \fbox{\epsffile{#1}}}

% my standard epsf (centered, full width)
\newcommand{\mysepsf}[1]{\mycepsf{#1}{1}}

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

% my new centered epsf (centered, width set to given fraction of textwidth)
\newcommand{\mynewcepsf}[2]{\centerline{\epsfig{width=#2\textwidth, file=#1}}}
% my new centered epsf (centered, width set to given fraction of textwidth)
\newcommand{\mynewchepsf}[3]{\centerline{\epsfig{width=#2\textwidth, height=#3,file=#1}}}
% my new centered and boxed epsf
\newcommand{\mynewcbepsf}[2]{\centerline{\fbox{\epsfig{width=#2\textwidth, file=#1}}}}
% my new standard epsf (centered, full width)
\newcommand{\mynewsepsf}[1]{\mynewcepsf{#1}{1}}
% my new standard height epsf (centered, full width, specified height)
\newcommand{\mynewshepsf}[2]{\mynewchepsf{#1}{1}{#2}}


\newcommand{\A}{{\cal A}}
\newcommand{\bw}{\mbox{\bf w}}
\newcommand{\bxi}{\mbox{\boldmath$\xi$}}

\title{\htmladdnormallink{DemoGNG v1.2}{../../GNG.html}}
\author{\htmladdnormallink{\emph{Hartmut S. Loos}}{http://www.neuroinformatik.ruhr-uni-bochum.de/ini/PEOPLE/loos}\\
\emph{and} \\
\htmladdnormallink{\emph{Bernd Fritzke}}{http://www.neuroinformatik.ruhr-uni-bochum.de/ini/PEOPLE/fritzke}\\ \\
\htmladdnormallink{Systems Biophysics}{http://www.neuroinformatik.ruhr-uni-bochum.de/ini/VDM/top.html}\\Institute for Neural
  Computation\\Ruhr-Universit\"at Bochum\\~\\~\htmladdimg{../java_powered.gif}}
\begin{document}

\maketitle 
\begin{abstract}
  DemoGNG, a Java applet, implements several methods related to
  competitive learning. It is possible to experiment with the
  methods using various data distributions and observe the learning process.
  A common terminology is used to make it easy to compare one method
  to the other. 
  Thanks to the Java programming language the implementations run on a
  very large number of platforms without the need of compilation or
  local adaptation. Hopefully, the experimentation with the models
  will increase the intuitive understanding and make it easier to
  judge their particular strengths and weaknesses.

%  \begin{rawhtml}
%    This document is available in <a href="../../README"> ASCII</a>-, <a
%    href="../DemoGNG.dvi"> DVI</a>-, and <a href="../DemoGNG.ps"> Postscript</a>-Format.
%  \end{rawhtml}
\end{abstract}

\newpage

\tableofcontents
\vspace{2cm}
\listoffigures
\newpage

\section{Introduction}

In the area of competitive learning a rather large number of models exist
which have similar goals but differ considerably  in the way they work. A
common goal of those algorithms is to distribute a certain number of vectors
in a possibly high-dimensional space. The distribution of these vectors should
reflect (in one of several possible ways) the distribution of input signals
which in general is not given explicitly but only through sample vectors.


\section{System Requirements}
To run DemoGNG, a Web browser with Java enhancements
(e.g. \htmladdnormallink{Netscape}{http://home.netscape.com} 2.0 or newer, 
\htmladdnormallink{Microsofts Internet Explorer}{http://www.microsoft.com},
...) is needed or ,e.g. the \htmladdnormallink{Sun
  Microsystems}{http://java.sun.com} appletviewer from the Java
Developers Kit (JDK). 

%The JDK is only needed for developement. All necessary files
%are included in the tar archive. The JDK can be obtained for Linux
%from \newline
%\htmladdnormallink{http://www.blackdown.org/java-linux/Mirrors.html}{http://www.blackdown.org/java-linux/Mirrors.html}\newline
%and for other operating systems from \newline
%\htmladdnormallink{http://java.sun.com/java.sun.com/products/JDK/index.html}{http://java.sun.com/java.sun.com/products/JDK/index.html}.

\section{Installation}
\htmladdnormallink{Download}{../../DemoGNGcode.html#download}
(\htmladdnormallink{ftp://ftp.neuroinformatik.ruhr-uni-bochum.de/pub/software/NN/DemoGNG/DemoGNG-1.2.tar.gz}{ftp://ftp.neuroinformatik.ruhr-uni-bochum.de/pub/software/NN/DemoGNG/DemoGNG-1.2.tar.gz})
the compressed
tar version, save it to a file, say DemoGNG-1.2.tar.gz, and then extract
the files with 

\begin{verbatim}
% gunzip DemoGNG-1.2.tar.gz
% tar xvf DemoGNG-1.2.tar
\end{verbatim}

Instead, you can \htmladdnormallink{download}{../../DemoGNGcode.html#download}
DemoGNG in zip-format (\htmladdnormallink{ftp://ftp.neuroinformatik.ruhr-uni-bochum.de/pub/software/NN/DemoGNG/DemoGNG-1.2.zip}{ftp://ftp.neuroinformatik.ruhr-uni-bochum.de/pub/software/NN/DemoGNG/DemoGNG-1.2.zip}).

After uncompressing and unpacking you should have the following: 

\begin{tabular}{lp{9cm}}
\texttt{COPYING}                 &       copy of the GNU General Public License \\
\texttt{Changes}                 &       change history for DemoGNG \\
\texttt{DemoGNG.java}            &       Java source for DemoGNG \\
\texttt{ComputeGNG.java}        &       Java source for DemoGNG \\
\texttt{DemoGNG.java}           &       Java source for DemoGNG \\
\texttt{EdgeGNG.java}           &       Java source for DemoGNG \\
\texttt{EdgeVoronoi.java}       &       Java source for DemoGNG \\
\texttt{FPoint.java}            &       Java source for DemoGNG \\
\texttt{GraphGNG.java}          &       Java source for DemoGNG \\
\texttt{GridNodeGNG.java}       &       Java source for DemoGNG \\
\texttt{HalfEdgeVoronoi.java}   &       Java source for DemoGNG \\
\texttt{LineGNG.java}           &       Java source for DemoGNG \\
\texttt{ListElem.java}          &       Java source for DemoGNG \\
\texttt{ListGNG.java}           &       Java source for DemoGNG \\
\texttt{NodeGNG.java}           &       Java source for DemoGNG \\
\texttt{SelGraphics.java}       &       Java source for DemoGNG \\
\texttt{SiteVoronoi.java}       &       Java source for DemoGNG \\

\texttt{DemoGNGcode.html}        &       starting page for source documentation \\
\texttt{GenerateHTML.tcl}        &       a tcl-script to generate some
                                         html-pages with different parameters \\
\texttt{Makefile}                &       Makefile for Unix 'make' \\
\texttt{README}                  &       the ASCII-version of this document \\
\texttt{SwitchGNG.html}          &       the main html-page \\
\texttt{audio/}                  &       subdirectory containing audio
                                         files. \\
\texttt{doc/}                    &       subdirectory containing the javadoc
                                         generated documentation of DemoGNG
                                         with the needed images.\\
\texttt{tex/}                    &       subdirectory containing the LaTeX 
                                         source of the manual with the
                                         dvi-, ps- and html-format.
\end{tabular}


Type {\texttt make world} to generate some necessary files (all these files are
included in the archive).

\begin{tabular}{lp{9cm}}
 \texttt{*.html}          &       needed for SwitchGNG.html \\
 \texttt{*.class}         &       compiled classes \\
 \texttt{doc/*.html}      &       javadoc generated html-files
\end{tabular}


\section{Starting the Java Applet}

Start the Web browser with the main html-page.\newline
Example:
\begin{verbatim}
% netscape SwitchGNG.html
\end{verbatim}
Important: Make sure you have Java support enabled.

Instead, you can also use an appletviewer with one of the generated
html-files.\newline
Example:
\begin{verbatim}
% appletviewer GNG.html
\end{verbatim}
Important: The appletviewer requires an applet included in the Web
           page, so you must choose one of the generated html-files.


\section{Manual}

\begin{figure}[htb]
  \begin{center}
    \epsfig{file=eps/all_plus.ps, width=\textwidth}
    \caption{Overview}
  \end{center}
\end{figure}

After the Java applet has been launched, the DemoGNG main window
appears. This window can be divided into four regions:

\begin{enumerate}
\item Network Model
\item Drawing Area
\item General Options
\item Model Specific Options
\end{enumerate}

\subsection{Network Model} \label{Network_Model}

\begin{figure}[htb]
  \begin{center}
    \epsfig{file=eps/modell-menu.ps, width=3cm}
    \caption{Pull-down menu with all available modells}
  \end{center}
\end{figure}

The first part shows the actual algorithm. To select another algorithm
or restart the current, click on the pull-down menu and choose the
desired algorithm. 
The following algorithms are available:
\begin{itemize}
\item Growing Neural Gas (Fritzke 1994, 1995 \cite{Fritzke94a,Fritzke95})
\item Hard Competitive Learning (standard algorithm)
\item Neural Gas (Martinetz and Schulten 1991 \cite{Martinetz91})
\item Neural Gas with Competitive Hebbian Learning (Martinetz and
  Schulten 1991, 1994 \cite{Martinetz91,Martinetz94})  
\item Competitive Hebbian Learning (Martinetz and Schulten 1991
  \cite{Martinetz91}, Martinetz 1993 \cite{Martinetz93}) 
\item LBG (Linde, Buzo and Gray 1980 \cite{Linde80})
\item Growing Grid (Fritzke 1995 \cite{Fritzke95b})
\item Self-Organizing Map (Kohonen 1982 \cite{Kohonen82b})
\end{itemize}

\newcommand{\pwida}{0.48}
\begin{figure}[htb]
\begin{minipage}[b]{\pwida\textwidth}
  \mysepsf{eps/GNG_Teach.ps}
  \centerline{Growing Neural Gas}
  \medskip
\end{minipage}
\hfill
\begin{minipage}[b]{\pwida\textwidth}
  \mysepsf{eps/HCL_Voronoi.ps}
  \centerline{Hard Competitive Learning}
  \medskip
\end{minipage}
\hfill
\begin{minipage}[b]{\pwida\textwidth}
  \mysepsf{eps/NG.ps}
  \centerline{Neural Gas}
  \medskip
\end{minipage}
\hfill
\begin{minipage}[b]{\pwida\textwidth}
  \mysepsf{eps/NGwCHL.ps}
  \centerline{Neural Gas with CHL}
  \medskip
\end{minipage}
\hfill
\begin{minipage}[b]{\pwida\textwidth}
  \mysepsf{eps/CHL_Signals.ps}
  \centerline{Competitive Hebbian Learning}
  \medskip
\end{minipage}
\hfill
\begin{minipage}[b]{\pwida\textwidth}
  \mysepsf{eps/LBG_Delaunay.ps}
  \centerline{LBG}
  \medskip
\end{minipage}
\hfill
\begin{minipage}[b]{\pwida\textwidth}
  \mysepsf{eps/GG.ps}
  \centerline{Growing Grid}
  \medskip
\end{minipage}
\hfill
\begin{minipage}[b]{\pwida\textwidth}
  \mysepsf{eps/SOM.ps}
  \centerline{Self-Organizing Map}
  \medskip
\end{minipage}
\caption{Example screenshots of the available models} 
\end{figure}

%\begin{figure}[htb]
%\begin{center}
%  \epsfig{width=5.5cm,file=eps/GNG_Teach.ps}
%  \epsfig{width=5.5cm,file=eps/HCL_Voronoi.ps} \\[1mm]
%  \epsfig{width=5.5cm,file=eps/NG.ps}
%  \epsfig{width=5.5cm,file=eps/NGwCHL.ps} \\[1mm]
%  \epsfig{width=5.5cm,file=eps/CHL_Signals.ps}
%  \epsfig{width=5.5cm,file=eps/LBG_Delaunay.ps} \\[1mm]
%  \epsfig{width=5.5cm,file=eps/GG.ps}
%  \epsfig{width=5.5cm,file=eps/SOM.ps}
%\caption{Example screenshots of the available models} 
%\end{center} 
%\end{figure}

\subsection{Drawing Area}

The drawing area shows the network for the selected algorithm. The
geometric figure in the background of the area reflects the
\hyperref
               % This will be highlighted in the hypertext version
{probability distribution}                      % argument #1
               % This will be shown in the printed version 
               % followed by a numeric reference ...      
{probability distribution (see Section }        % argument #2
               % ... followed by this text
{ for more information)}                % argument #3
               % This the common label 
{General_Options_PDM}. In every phase of the
algorithm you can select a node and drag it to an arbitrary location within
the drawing area.
Additional information is displayed in the corners of this region:

\begin{tabular}{ll}
upper left  & Number of input signals occured so far \\
upper right & Version number \\
lower left  & Number of nodes \\
lower right & Some additional information
\end{tabular}


\subsection{General Options}

\begin{figure}[htb]
  \begin{center}
    \epsfig{file=eps/options.ps, width=10cm}
    \caption{Options for all modells}
  \end{center}
\end{figure}

This region contains the non-specific parameters for all
algorithms. There are three kinds of interface elements: buttons,
checkboxes and pull-down-menus. 

\subsubsection{Buttons}
\begin{tabular}{lp{10cm}}
Start   &       Starts/Continues a stopped run. \\
Stop    &       Stops a calculation to modify parameters or move nodes
                (not necessary to stop, but you have more time).\\
Reset   &       Resets the algorithm, but leave all parameters
                unchanged (to restart an 
                \hyperref
                % This will be highlighted in the hypertext version
                {algorithm with default parameters}  % argument #1
                % This will be shown in the printed version 
                % followed by a numeric reference ...      
                {algorithm with default parameters see Section } % argument #2
                % ... followed by this text
                { for more information} % argument #3
                % This the common label 
                {Network_Model}). 
\end{tabular}

\subsubsection{Checkboxes}

\newcommand{\pwidb}{0.32}
\begin{figure}[htb]
\begin{minipage}[b]{\pwidb\textwidth}
  \mysepsf{eps/GNG_Teach.ps}
  \centerline{Teach mode}
\end{minipage}
\hfill
\begin{minipage}[b]{\pwidb\textwidth}
  \mysepsf{eps/HCL_Voronoi.ps}
  \centerline{Voronoi diagram}
\end{minipage}
\hfill
\begin{minipage}[b]{\pwidb\textwidth}
  \mysepsf{eps/ErrorGraph.ps}
  \centerline{Error graph}
\end{minipage}
\caption{Some examples for activated checkboxes.} 
\end{figure}


\begin{tabular}{lp{10cm}}
Teach   &       Switches teach mode on and off. The algorithm is slowed
                down and more information is displayed
                depending on the algorithm. \\ 
Signals &       Switches signals on and off. The most recently
                generated signals are shown. \\
Voronoi &       Displays Voronoi diagram. \\
Delaunay &      Displays Delaunay triangulation. \\
Error Graph &   Switches the error graph on and off. It is displayed in
                an extra window and shows the mean square error of the
                selected model. \\
Nodes &         Turns the display of nodes on and off. \\
Edges &         Turns the display of edges on and off. \\
White &         Switches the background of the drawing area to white.
                This is useful for making hardcopies of the screen. \\
Sound   &       Switches sound on and off.
\end{tabular}

\subsubsection{Pull-Down Menus} \label{General_Options_PDM}

\begin{figure}[htb]
\begin{minipage}[b]{2cm}
  \mynewsepsf{eps/Distributions.ps} \hfill