ROOT logo
ROOT » TMVA » TMVA::TActivationSigmoid

class TMVA::TActivationSigmoid: public TMVA::TActivation


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


Function Members (Methods)

Data Members

private:
TFormula*fEqnequation of sigmoid
TFormula*fEqnDerivativeequation of sigmoid derivative

Class Charts

Inheritance Inherited Members Includes Libraries
Class Charts

Function documentation

TActivationSigmoid()
 constructor for sigmoid normalized in [0,1]
~TActivationSigmoid()
 destructor
Double_t Eval(Double_t arg)
 evaluate the sigmoid
Double_t EvalDerivative(Double_t arg)
 evaluate the derivative of the sigmoid
TString GetExpression()
 get expressions for the sigmoid and its derivatives
void MakeFunction(ostream& fout, const TString& fncName)
 writes the sigmoid activation function source code
TActivationSigmoid()
Double_t GetMin()
 minimum of the range of the activation function
{ return 0; }
Double_t GetMax()
 maximum of the range of the activation function
{ return 1; }