library: libTMVA #include "TMVA_MethodTMlpANN.h" |
TMVA_MethodTMlpANN
class description - source file - inheritance tree (.pdf)
private:
void CreateMLPOptions()
void InitTMlpANN()
public:
TMVA_MethodTMlpANN(TString jobName, vector<TString>* theVariables, TTree* theTree = 0, TString theOption = 3000:N-1:N-2, TDirectory* theTargetDir = 0)
TMVA_MethodTMlpANN(vector<TString>* theVariables, TString theWeightFile, TDirectory* theTargetDir = NULL)
TMVA_MethodTMlpANN(const TMVA_MethodTMlpANN&)
virtual ~TMVA_MethodTMlpANN()
static TClass* Class()
virtual Double_t GetMvaValue(TMVA_Event*)
virtual TClass* IsA() const
TMVA_MethodTMlpANN& operator=(const TMVA_MethodTMlpANN&)
virtual void PrepareEvaluationTree(TTree* testTree)
virtual void ReadWeightsFromFile()
void SetHiddenLayer(TString hiddenlayer = )
void SetTestTree(TTree* testTree)
virtual void ShowMembers(TMemberInspector& insp, char* parent)
virtual void Streamer(TBuffer& b)
void StreamerNVirtual(TBuffer& b)
virtual void Train()
virtual void WriteHistosToFile()
virtual void WriteWeightsToFile()
private:
TString fHiddenLayer string containig the hidden layer structure
Int_t fNcycles number of training cylcles
TTree* fTestTree TestTree
This is the TMVA TMultiLayerPerceptron interface class. It provides the
training and testing the ROOT internal MLP class in the TMVA framework
available learning methods:
TMultiLayerPerceptron::kStochastic
TMultiLayerPerceptron::kBatch
TMultiLayerPerceptron::kSteepestDescent
TMultiLayerPerceptron::kRibierePolak
TMultiLayerPerceptron::kFletcherReeves
TMultiLayerPerceptron::kBFGS
_______________________________________________________________________
TMVA_MethodTMlpANN( TString jobName, std::vector<TString>* theVariables,
TTree* theTree, TString theOption, TDirectory* theTargetDir)
: TMVA_MethodBase(jobName, theVariables, theTree, theOption, theTargetDir )
standard constructor which is called by the TMVA_Factory for testing and training
TMVA_MethodTMlpANN( vector<TString> *theVariables,
TString theWeightFile,
TDirectory* theTargetDir )
: TMVA_MethodBase( theVariables, theWeightFile, theTargetDir )
constructor for TMlpANN method which can only be used for reading a weight file and testing
void InitTMlpANN( void )
~TMVA_MethodTMlpANN( void )
void CreateMLPOptions( void )
parse the option string
void Train( void )
trainning method
performs training of the neural net. available learning methods:
TMultiLayerPerceptron::kStochastic
TMultiLayerPerceptron::kBatch
TMultiLayerPerceptron::kSteepestDescent
TMultiLayerPerceptron::kRibierePolak
TMultiLayerPerceptron::kFletcherReeves
TMultiLayerPerceptron::kBFGS
void WriteWeightsToFile( void )
write weights to file
void ReadWeightsFromFile( void )
read weights from file
void PrepareEvaluationTree( TTree* testTree )
evaluate method
void SetTestTree( TTree* testTree )
void WriteHistosToFile( void )
Inline Functions
Double_t GetMvaValue(TMVA_Event*)
void SetHiddenLayer(TString hiddenlayer = )
TClass* Class()
TClass* IsA() const
void ShowMembers(TMemberInspector& insp, char* parent)
void Streamer(TBuffer& b)
void StreamerNVirtual(TBuffer& b)
TMVA_MethodTMlpANN TMVA_MethodTMlpANN(const TMVA_MethodTMlpANN&)
TMVA_MethodTMlpANN& operator=(const TMVA_MethodTMlpANN&)
Author: Andreas Hoecker, Helge Voss, Kai Voss
Last update: root/tmva $Id: TMVA_MethodTMlpANN.cxx,v 1.2 2006/05/09 08:37:06 brun Exp $
Copyright (c) 2005: *
ROOT page - Class index - Class Hierarchy - Top of the page
This page has been automatically generated. If you have any comments or suggestions about the page layout send a mail to ROOT support, or contact the developers with any questions or problems regarding ROOT.