<br/> 
<hr/> 
<a name="tmva"></a> 
<h3>TMVA</h3>

TMVA version 4.1.2 is included in this root release. The changes with respect
to ROOT 5.28 / TMVA 4.1.0 are in detail:

<h4>Variable transformations</h4>
<ul>
      <li>Variable transformations can now be applied to a user-defined subset
        of variables (and regression targets).</li>

      <li>Enable variable transformations for general boosting</li>

      <li>Extended PDEFoam functionality:<br>
        <ul>
          <li>Multiclass classification by training of one discriminator foam for each
            variable.</li>
          
          <li>The cell tree can now be plotted from the macro test/PlotFoams. This makes
            it easyer to compare the PDEFoam structure to a decision tree.</li>
          <li>Variable importance ranking by counting the number of cuts made in each
            dimension.  The variable, for which the most cuts were done is ranked highest.</li>
         </ul>
   </li>
      <li>Fixed the size of the sampling box in PDEFoam:
        In TMVA 4.1.0 the size of the PDEFoam sampling box in each dimension was
        2*VolFrac times the foam size.  This was contrary to the intention and the
        documentation in the UserGuide and is now corrected: In TMVA 4.1.1 the size
        of the PDEFoam sampling box in each dimension is now VolFrac times the foam
        size. This implies that in TMVA 4.1.1 the VolFrac value for training a PDEFoam
        must be doubled in order to give the same results as in TMVA 4.1.0.  The default
        VolFrac value was also changed from 0.0333 to 0.0666.</li>

      <li>New configuration variable "NbinsMVAoutput" defining the bins of the MVA output
    variables in the TMVA training plots produced via the GUI. As always, Config
    settings can be modified in the training script via, eg, the command

        (TMVA::gConfig().GetVariablePlotting()).fNbinsMVAoutput = 50;

    to be called AFTER initialising the TMVA Factory object.</li>
</ul>

<h4>Bug fixes</h4>
<ul>

    <li>Requested number of training and testing events was not
    correct when pre-selection cuts were applied. Now the number of
    requested events scales with the preselection efficiency and hence
    does not need to be adjusted with the pre-selection. This also
    corrects the problems seen in the Category classifierm, where
    pre-selection is used to build the categories.</li>
    <li>Correct histogram boundaries in PlotVariable.</li>
    <li>Correct scanning procedure in OptimizeTuningParameters.</li>
    <li>Print the significance formula that is actually used</li>
    <li>Small speed improvement for PDEFoam functions.</li>
    <li>Fix for MethodBoost which ensures that the method options for the boosted
       classifier are handled correctly during boosting.</li>
    <li>Fixed problems in classification of some methods when booking background
       training tree before signal one.</li>
    <li>Fixed preprocessing transformation bug in HMatrix</li>
    <li>Several minor bug fixes for version 4.1.2</li>
</ul>