prtClassBinaryToMaryOneVsAll  M-Ary Emulation Classifier
 
     CLASSIFIER = prtClassBinaryToMaryOneVsAll returns a M-ary "one
     versus all" classifier. A one versus all classifier utilizes a
     binary classifier to make M-ary decisions. For all M classes, it
     selects each class, and makes a binary comparison to all the
     others.
 
     CLASSIFIER = prtClassBinaryToMaryOneVsAll(PROPERTY1, VALUE1, ...)
     constructs a prtClassBinaryToMaryOneVsAll object CLASSIFIER with
     properties as specified by PROPERTY/VALUE pairs.
 
     A prtClassBinaryToMaryOneVsAll object inherits all properties from the
     abstract class prtClass. In addition is has the following
     properties:
 
     baseClassifier - The classifier to be used to make the binary
                   decisions. Must be a prtClass object, and defaults 
                   to a prtClassLogisticDiscriminant classifier.
  
     A prtClassBinaryToMaryOneVsAll object inherits the TRAIN, RUN,
     CROSSVALIDATE and KFOLDS methods from prtAction. It also inherits
     the PLOT method from prtClass.
 
     Example:
 
      TestDataSet = prtDataGenMary;      % Create some test and 
      TrainingDataSet = prtDataGenMary;  % training data
      classifier = prtClassBinaryToMaryOneVsAll;   % Create a classifier
      classifier.baseClassifier = prtClassGlrt;    % Set the binary 
                                                   % Classifier
      % Set the internal Decider
      classifier.internalDecider = prtDecisionMap;
 
      classifier = classifier.train(TrainingDataSet);    % Train
      classes    = run(classifier, TestDataSet);         % Test
 
      % Evaluate, plot results
      percentCorr = prtScorePercentCorrect(classes.getX,TestDataSet.getTargets)
      classifier.plot;