prtRegressRvm  Relevance vector machine regression object
 
    REGRESS = prtRegressRvm returns a prtRegressRvm object
 
     REGRESS = prtRegressRVM(PROPERTY1, VALUE1, ...) constructs a
     prtRegressRvm object REGRESS with properties as specified by
     PROPERTY/VALUE pairs.
  
     A prtRegressRvm object inherits all properties from the prtRegress
     class. In addition, it has the following properties:
 
    SetAccess = public:
     kernels            - A cell array of prtKernel objects specifying
                          the kernels to use
     verbosePlot        - Flag indicating whether or not to plot during
                          training
     verboseText        - Flag indicating whether or not to display
                          a message during training
 
    SetAccess = private/protected:
     learningConverged  - Flag indicating if the training converged
     learningResults    - Struct with information about the convergence
     beta               - The weights on each of the kernel elements;
                          learned during training
     Sigma              - The learned covariance
     sparseBeta         - The weights on the retained kernel elements;
                          learned durning training
     sparseKernels      - The retained kernels
 
    This code is based on:
        Michael E Tipping, Sparse bayesian learning and the relevance 
    vector machine, The Journal of Machine Learning Research, Vol 1.
 
    Also see http://en.wikipedia.org/wiki/Relevance_vector_machine
  
    A prtRegressionRvm object inherits the PLOT method from the
    prtRegress object, and the TRAIN, RUN, CROSSVALIDATE and KFOLDS
    methods from the prtAction object.
 
    Example:
    
    dataSet = prtDataGenNoisySinc;           % Load a prtDataRegress
    dataSet.plot;                    % Display data
    reg = prtRegressRvm;             % Create a prtRegressRvm object
    reg = reg.train(dataSet);        % Train the prtRegressRvm object
    reg.plot();                      % Plot the resulting curve
    dataSetOut = reg.run(dataSet);   % Run the regressor on the data
    hold on;
    plot(dataSet.getX,dataSetOut.getX,'c.') % Plot, overlaying the
                                            % fitted points with the 
                                            % curve and original data
    legend('Regression curve','Original Points','Kernel Locations Used',0)