prtRvUniformImproper  Improper uniform random variable
 
    RV = prtRvUniformImproper creates a prtRvUniformImproper object
    with unknown dimensionality nDimensions. nDimensions can be set
    manually or using the MLE method. A prtRvUniformImproper
    models an improper pdf that always yields a value of 1 no matter
    the input. prtRvUniformImproper is sometimes useful for creating 
    one class classifiers. See the examples below for more information
 
    The draw method of prtRvUniformImproper draws values uniformly
    distributed from realmin to realmax in each dimension.
 
    RV = prtRvUniformImproper(PROPERTY1, VALUE1,...) creates a
    prtRvMultinomial object RV with properties as specified by
    PROPERTY/VALUE pairs.
 
    A prtRvUniformImproper object inherits all properties from the
    prtRv class. In addition, it has the following properties:
 
    nDimensions - dimensionality of the data modeled by this RV.
    
   A prtRvUniformImproper object inherits all methods from the prtRv
   class. The MLE  method can be used to set the parameters from data.
 
   Example:
 
   % In this example we show that the PDF of a prtRvUniformImproper is
   % always 1
   dataSet = prtDataGenUnimodal;        % Load a dataset consisting of
                                        % 2 features
   dataSet = retainFeatures(dataSet,1); % Retain only the first feature
                                        % only for the example.
 
   RV = prtRvUniformImproper;           % Create a prtRvUniform object
   RV = RV.mle(dataSet);                % Compute the bounds
 
   RV.plotPdf([-10 10]);                % We must manually specify
                                        % plot limits since
                                        % prtRvUniformImproper does not
                                        % have actual plot limits
 
 
   % In this example we show how to build a one class MAP classifier
   dataSet = prtDataGenUnimodal;        % Load a dataset consisting of
                                        % 2 features
   
   % Create and train a GLRT classifier that uses a 
   % prtRvUniformImproper to model class 0 and a prtRvMvn to model
   % class 1
   glrtClass = train(prtClassGlrt('rvH0',prtRvUniformImproper,'rvH1',prtRvMvn),dataSet);
 
   plot(glrtClass) % Contours only show the log-likelihood of class 1