class TMVA::MethodCFMlpANN: public TMVA::MethodBase, private TMVA::MethodCFMlpANN_Utils

 standard constructor
 option string: "n_training_cycles:n_hidden_layers"
 default is:  n_training_cycles = 5000, n_layers = 4

 * note that the number of hidden layers in the NN is:
   n_hidden_layers = n_layers - 2

 * since there is one input and one output layer. The number of
   nodes (neurons) is predefined to be:
   n_nodes[i] = nvars + 1 - i (where i=1..n_layers)

   with nvars being the number of variables used in the NN.

 Hence, the default case is: n_neurons(layer 1 (input)) : nvars
                             n_neurons(layer 2 (hidden)): nvars-1
                             n_neurons(layer 3 (hidden)): nvars-1
                             n_neurons(layer 4 (out))   : 2

 This artificial neural network usually needs a relatively large
 number of cycles to converge (8000 and more). Overtraining can
 be efficienctly tested by comparing the signal and background
 output of the NN for the events that were used for training and
 an independent data sample (with equal properties). If the separation
 performance is significantly better for the training sample, the
 NN interprets statistical effects, and is hence overtrained. In
 this case, the number of cycles should be reduced, or the size
 of the training sample increased.

 constructor from weight file

 CFMlpANN can handle classification with 2 classes

 define the options (their key words) that can be set in the option string
 know options: NCycles=xx              :the number of training cycles
               HiddenLayser="N-1,N-2"  :the specification of the hidden layers

 decode the options in the option string

 default initialisation called by all constructors

 destructor

 training of the Clement-Ferrand NN classifier

 returns CFMlpANN output (normalised within [0,1])

 evaluates NN value as function of input variables

 auxiliary functions

 activation function

 read back the weight from the training from file (stream)

 data interface function

 write weights to xml file

 read weights from xml file

 write the weights of the neural net

 static pointer to this object (required for external functions

 write specific classifier response

 write specific classifier response for header

 get help message text

 typical length of text line:
         "|--------------------------------------------------------------|"

 data accessors for external functions

 ranking of input variables