ROOT logo
ROOT » TMVA » TMVA::TActivationTanh

class TMVA::TActivationTanh: public TMVA::TActivation

  Tanh activation function for ANN. This really simple implementation
  uses TFormulas and should probably be replaced with something more
  efficient later.

Function Members (Methods)

static TClass*Class()
virtual Double_tEval(Double_t arg)
virtual Double_tEvalDerivative(Double_t arg)
virtual TStringGetExpression()
virtual Double_tGetMax()
virtual Double_tGetMin()
virtual TClass*IsA() const
virtual voidMakeFunction(ostream& fout, const TString& fncName)
TMVA::TActivationTanh&operator=(const TMVA::TActivationTanh&)
virtual voidShowMembers(TMemberInspector& insp, char* parent)
virtual voidStreamer(TBuffer& b)
voidStreamerNVirtual(TBuffer& b)
TMVA::TActivationTanhTActivationTanh(const TMVA::TActivationTanh&)

Data Members

TFormula*fEqnequation of tanh sigmoid
TFormula*fEqnDerivativeequation of tanh sigmoid derivative

Class Charts

Inheritance Inherited Members Includes Libraries
Class Charts

Function documentation

 constructor for tanh sigmoid (normalized in [-1,1])
Double_t Eval(Double_t arg)
 evaluate the tanh
Double_t EvalDerivative(Double_t arg)
 evaluate the derivative
TString GetExpression()
 get expressions for the tanh and its derivative
void MakeFunction(ostream& fout, const TString& fncName)
 writes the sigmoid activation function source code
Double_t GetMin()
 minimum of the range of the activation function
{ return -1; }
Double_t GetMax()
 maximum of the range of the activation function
{ return 1; }