function slide=demolvq1
% This is a slideshow file for use with playshow.m and makeshow.m
% To see it run, type 'playshow demolvq1', 

% Copyright (c) 1992-1998 by The MathWorks, Inc.
% $Revision: 1.10 $  $Date: 1998/06/11 16:23:43 $

if nargout<1,
  playshow demolvq1
else
  %========== Slide 1 ==========

  slide(1).code={
   'slideData=nnslides(''start'',slideData,''Pattern Classification with a Learning Vector Quantization'');' };
  slide(1).text={
   'NEWLVQ  - Creates a LVQ network.',
   'TRAIN - Trains a neural network.',
   'SIM  - Simulates a neural network.',
   '',
   'An LVQ network is trained to classify input vectors according to given targets'};

  %========== Slide 2 ==========

  slide(2).code={
   'slideData=nnslides(''blank'',slideData);',
   'P = [-3 -2 -2  0  0  0  0 +2 +2 +3;  0 +1 -1 +2 +1 -1 -2 +1 -1  0];',
   ' C = [1 1 1 2 2 2 2 1 1 1];',
   'T = ind2vec(C);' };
  slide(2).text={
   'Here are 10 2-element example input vectors.',
   '>> P = [-3 -2 -2  0  0  0  0 +2 +2 +3;',
   '            0 +1 -1 +2 +1 -1 -2 +1 -1  0];',
   'Here are the classes these vectors fall into.',
   '>> C = [1 1 1 2 2 2 2 1 1 1];',
   'These classes can be transformed into vectors to be used as targets for the LVQ network.',
   '>> T = ind2vec(C);',
   ''};

  %========== Slide 3 ==========

  slide(3).code={
   'slideData=nnslides(''axes'',slideData);',
   'colormap(hsv)',
   'plotvec(P,C)',
   'title(''Input Vectors'');',
   'xlabel(''P(1)'');',
   'ylabel(''P(2)'');',
   '' };
  slide(3).text={
   'Here the data points are plotted.',
   '>> colormap(hsv)',
   '>> plotvec(P,C)',
   '>> title(''Input Vectors''); xlabel(''P(1)''); ylabel(''P(2)'');',
   'Red = class 1, Cyan = class 2.  The LVQ network represents clusters of vectors with hidden neurons, and groups the clusters with output neurons to form the desired classes.',
   '',
   ''};

  %========== Slide 4 ==========

  slide(4).code={
   'net = newlvq(minmax(P),4,[.6 .4],0.1);',
   '' };
  slide(4).text={
   'NEWLVQ creates an LVQ layer and here takes four arguments:',
   '>> net = newlvq(minmax(P),4,[.6 .4],0.1);',
   '1) Rx2 matrix of min and max values for R input elements',
   '2) number of hidden neurons',
   '3) element vector of typical class percentages',
   '4) learning rate',
   ''};

  %========== Slide 5 ==========

  slide(5).code={
   'cla;',
   'plotvec(P,C)',
   'hold on',
   'W1=net.IW{1};',
   'plot(W1(1,1),W1(1,2),''ow'')',
   'title(''Input/Weight Vectors'');',
   'xlabel(''P(1), W(1)'');',
   'ylabel(''P(2), W(3)'');',
   'hold off;' };
  slide(5).text={
   'The competitive neuron weight vectors are plotted as follows:',
   '>> hold on',
   '>> W=net.IW{1};',
   '>> plot(W(1,1),W(1,2),''ow'')',
   '>> title(''Input/Weight Vectors'');',
   '>> xlabel(''P(1), W(1)'');  ylabel(''P(2), W(3)'');',
   ''};

  %========== Slide 6 ==========

  slide(6).code={
   'slideData=nnslides(''lock'',slideData);',
   'cla;',
   'plotvec(P,C);',
   'hold on;',
   'net.trainParam.epochs=150;',
   'net.trainParam.show=Inf;',
   'net=train(net,P,T);',
   'plotvec(net.IW{1}'',vec2ind(net.LW{2}),''o'');',
   'slideData=nnslides(''unlock'',slideData);' };
  slide(6).text={
   'To train the network, first override the default number of epochs:',
   '>> net.trainParam.epochs=150;',
   'Then begin training.  It may take several seconds, so please wait:',
   '>> net=train(net,P,T);',
   'Replot the input vectors ''+'' and the competitive neurons'' weight vectors ''o''.',
   'Red = class 1, Cyan = class 2.',
   '>> plotvec(P,C);  hold on;',
   '>> plotvec(net.IW{1}'',vec2ind(net.LW{2}),''o'');'};

  %========== Slide 7 ==========

  slide(7).code={
   'p = [0.2; 1];',
   'a = vec2ind(sim(net,p));',
   '' };
  slide(7).text={
   'Now use the LVQ network as a classifier, where each neuron corresponds to a different category.  Present the input vector [0.2; 1].',
   '',
   '>> p = [0.2; 1];',
   '>> a = vec2ind(sim(net,p))',
   'a =',
   '    2',
   'Red = class 1, Cyan = class 2.',
   ''};
end