Definition at line 93 of file MethodMLP.h.

Public Types
enum	ETrainingMethod { kBP =0, kBFGS, kGA }

enum	EBPTrainingMode { kSequential =0, kBatch }

Public Types inherited from TMVA::MethodANNBase
enum	EEstimator { kMSE =0, kCE }

Public Types inherited from TMVA::MethodBase
enum	EWeightFileType { kROOT =0, kTEXT }

Public Types inherited from TObject
enum	EStatusBits { kCanDelete = BIT(0), kMustCleanup = BIT(3), kObjInCanvas = BIT(3), kIsReferenced = BIT(4), kHasUUID = BIT(5), kCannotPick = BIT(6), kNoContextMenu = BIT(8), kInvalidObject = BIT(13) }

enum	{ kIsOnHeap = 0x01000000, kNotDeleted = 0x02000000, kZombie = 0x04000000, kBitMask = 0x00ffffff }

enum	{ kSingleKey = BIT(0), kOverwrite = BIT(1), kWriteDelete = BIT(2) }

Public Member Functions
	MethodMLP (const TString &jobName, const TString &methodTitle, DataSetInfo &theData, const TString &theOption, TDirectory *theTargetDir=0)

	MethodMLP (DataSetInfo &theData, const TString &theWeightFile, TDirectory *theTargetDir=0)
	constructor from a weight file More...

virtual	~MethodMLP ()
	destructor nothing to be done More...

virtual Bool_t	HasAnalysisType (Types::EAnalysisType type, UInt_t numberClasses, UInt_t numberTargets)
	MLP can handle classification with 2 classes and regression with one regression-target. More...

void	Train ()

Double_t	ComputeEstimator (std::vector< Double_t > &parameters)
	this function is called by GeneticANN for GA optimization More...

Double_t	EstimatorFunction (std::vector< Double_t > &parameters)
	interface to the estimate More...

bool	HasInverseHessian ()

Double_t	GetMvaValue (Double_t err=0, Double_t errUpper=0)
	get the mva value generated by the NN More...

Public Member Functions inherited from TMVA::MethodANNBase
	MethodANNBase (const TString &jobName, Types::EMVA methodType, const TString &methodTitle, DataSetInfo &theData, const TString &theOption, TDirectory *theTargetDir)

	MethodANNBase (Types::EMVA methodType, DataSetInfo &theData, const TString &theWeightFile, TDirectory *theTargetDir)
	construct the Method from the weight file More...

virtual	~MethodANNBase ()
	destructor More...

void	InitANNBase ()
	initialize ANNBase object More...

void	SetActivation (TActivation *activation)

void	SetNeuronInputCalculator (TNeuronInput *inputCalculator)

virtual void	PrintNetwork () const
	print network representation, for debugging More...

template<typename WriteIterator >
void	GetLayerActivation (size_t layer, WriteIterator writeIterator)

void	AddWeightsXMLTo (void *parent) const
	create XML description of ANN classifier More...

void	ReadWeightsFromXML (void *wghtnode)
	read MLP from xml weight file More...

virtual void	ReadWeightsFromStream (std::istream &istr)
	destroy/clear the network then read it back in from the weights file More...

virtual const std::vector< Float_t > &	GetRegressionValues ()
	get the regression value generated by the NN More...

virtual const std::vector< Float_t > &	GetMulticlassValues ()
	get the multiclass classification values generated by the NN More...

virtual void	WriteMonitoringHistosToFile () const
	write histograms to file More...

const Ranking *	CreateRanking ()
	compute ranking of input variables by summing function of weights More...

Bool_t	Debug () const
	who the hell makes such strange Debug flags that even use "global pointers".. More...

Public Member Functions inherited from TMVA::MethodBase
	MethodBase (const TString &jobName, Types::EMVA methodType, const TString &methodTitle, DataSetInfo &dsi, const TString &theOption="", TDirectory *theBaseDir=0)
	standard constructur More...

	MethodBase (Types::EMVA methodType, DataSetInfo &dsi, const TString &weightFile, TDirectory *theBaseDir=0)
	constructor used for Testing + Application of the MVA, only (no training), using given WeightFiles More...

virtual	~MethodBase ()
	destructor More...

void	SetupMethod ()
	setup of methods More...

void	ProcessSetup ()
	process all options the "CheckForUnusedOptions" is done in an independent call, since it may be overridden by derived class (sometimes, eg, fitters are used which can only be implemented during training phase) More...

virtual void	CheckSetup ()
	check may be overridden by derived class (sometimes, eg, fitters are used which can only be implemented during training phase) More...

void	AddOutput (Types::ETreeType type, Types::EAnalysisType analysisType)

void	TrainMethod ()

virtual std::map< TString, Double_t >	OptimizeTuningParameters (TString fomType="ROCIntegral", TString fitType="FitGA")
	call the Optimzier with the set of paremeters and ranges that are meant to be tuned. More...

virtual void	SetTuneParameters (std::map< TString, Double_t > tuneParameters)
	set the tuning parameters accoding to the argument This is just a dummy . More...

void	SetTrainTime (Double_t trainTime)

Double_t	GetTrainTime () const

void	SetTestTime (Double_t testTime)

Double_t	GetTestTime () const

virtual void	TestClassification ()
	initialization More...

virtual Double_t	GetKSTrainingVsTest (Char_t SorB, TString opt="X")

virtual void	TestMulticlass ()
	test multiclass classification More...

virtual void	TestRegression (Double_t &bias, Double_t &biasT, Double_t &dev, Double_t &devT, Double_t &rms, Double_t &rmsT, Double_t &mInf, Double_t &mInfT, Double_t &corr, Types::ETreeType type)
	calculate <sum-of-deviation-squared> of regression output versus "true" value from test sample More...

virtual void	DeclareCompatibilityOptions ()
	options that are used ONLY for the READER to ensure backward compatibility they are hence without any effect (the reader is only reading the training options that HAD been used at the training of the .xml weightfile at hand More...

virtual void	Reset ()

Double_t	GetMvaValue (const TMVA::Event const ev, Double_t err=0, Double_t *errUpper=0)

const std::vector< Float_t > &	GetRegressionValues (const TMVA::Event *const ev)

virtual Double_t	GetProba (const Event *ev)

virtual Double_t	GetProba (Double_t mvaVal, Double_t ap_sig)
	compute likelihood ratio More...

virtual Double_t	GetRarity (Double_t mvaVal, Types::ESBType reftype=Types::kBackground) const
	compute rarity: R(x) = Integrate_[-oo..x] { PDF(x') dx' } where PDF(x) is the PDF of the classifier's signal or background distribution More...

virtual void	MakeClass (const TString &classFileName=TString("")) const
	create reader class for method (classification only at present) More...

void	PrintHelpMessage () const
	prints out method-specific help method More...

void	WriteStateToFile () const
	write options and weights to file note that each one text file for the main configuration information and one ROOT file for ROOT objects are created More...

void	ReadStateFromFile ()
	Function to write options and weights to file. More...

void	ReadStateFromStream (std::istream &tf)
	read the header from the weight files of the different MVA methods More...

void	ReadStateFromStream (TFile &rf)
	write reference MVA distributions (and other information) to a ROOT type weight file More...

void	ReadStateFromXMLString (const char *xmlstr)
	for reading from memory More...

virtual void	WriteEvaluationHistosToFile (Types::ETreeType treetype)
	writes all MVA evaluation histograms to file More...

virtual Double_t	GetEfficiency (const TString &, Types::ETreeType, Double_t &err)
	fill background efficiency (resp. More...

virtual Double_t	GetTrainingEfficiency (const TString &)

virtual std::vector< Float_t >	GetMulticlassEfficiency (std::vector< std::vector< Float_t > > &purity)

virtual std::vector< Float_t >	GetMulticlassTrainingEfficiency (std::vector< std::vector< Float_t > > &purity)

virtual Double_t	GetSignificance () const
	compute significance of mean difference significance = \|<S> - \|/Sqrt(RMS_S2 + RMS_B2) More...

virtual Double_t	GetROCIntegral (TH1D histS, TH1D histB) const
	calculate the area (integral) under the ROC curve as a overall quality measure of the classification More...

virtual Double_t	GetROCIntegral (PDF pdfS=0, PDF pdfB=0) const
	calculate the area (integral) under the ROC curve as a overall quality measure of the classification More...

virtual Double_t	GetMaximumSignificance (Double_t SignalEvents, Double_t BackgroundEvents, Double_t &optimal_significance_value) const
	plot significance, S/Sqrt(S^2 + B^2), curve for given number of signal and background events; returns cut for maximum significance also returned via reference is the maximum significance More...

virtual Double_t	GetSeparation (TH1 , TH1 ) const
	compute "separation" defined as <s2> = (1/2) Int_-oo..+oo { (S(x) - B(x))^2/(S(x) + B(x)) dx } More...

virtual Double_t	GetSeparation (PDF pdfS=0, PDF pdfB=0) const
	compute "separation" defined as <s2> = (1/2) Int_-oo..+oo { (S(x) - B(x))^2/(S(x) + B(x)) dx } More...

virtual void	GetRegressionDeviation (UInt_t tgtNum, Types::ETreeType type, Double_t &stddev, Double_t &stddev90Percent) const

const TString &	GetJobName () const

const TString &	GetMethodName () const

TString	GetMethodTypeName () const

Types::EMVA	GetMethodType () const

const char *	GetName () const
	Returns name of object. More...

const TString &	GetTestvarName () const

const TString	GetProbaName () const

TString	GetWeightFileName () const
	retrieve weight file name More...

void	SetTestvarName (const TString &v="")

UInt_t	GetNvar () const

UInt_t	GetNVariables () const

UInt_t	GetNTargets () const

const TString &	GetInputVar (Int_t i) const

const TString &	GetInputLabel (Int_t i) const

const TString &	GetInputTitle (Int_t i) const

Double_t	GetMean (Int_t ivar) const

Double_t	GetRMS (Int_t ivar) const

Double_t	GetXmin (Int_t ivar) const

Double_t	GetXmax (Int_t ivar) const

Double_t	GetSignalReferenceCut () const

Double_t	GetSignalReferenceCutOrientation () const

void	SetSignalReferenceCut (Double_t cut)

void	SetSignalReferenceCutOrientation (Double_t cutOrientation)

TDirectory *	BaseDir () const
	returns the ROOT directory where info/histograms etc of the corresponding MVA method instance are stored More...

TDirectory *	MethodBaseDir () const
	returns the ROOT directory where all instances of the corresponding MVA method are stored More...

void	SetMethodDir (TDirectory *methodDir)

void	SetBaseDir (TDirectory *methodDir)

void	SetMethodBaseDir (TDirectory *methodDir)

UInt_t	GetTrainingTMVAVersionCode () const

UInt_t	GetTrainingROOTVersionCode () const

TString	GetTrainingTMVAVersionString () const
	calculates the TMVA version string from the training version code on the fly More...

TString	GetTrainingROOTVersionString () const
	calculates the ROOT version string from the training version code on the fly More...

TransformationHandler &	GetTransformationHandler (Bool_t takeReroutedIfAvailable=true)

const TransformationHandler &	GetTransformationHandler (Bool_t takeReroutedIfAvailable=true) const

void	RerouteTransformationHandler (TransformationHandler *fTargetTransformation)

DataSet *	Data () const

DataSetInfo &	DataInfo () const

UInt_t	GetNEvents () const
	temporary event when testing on a different DataSet than the own one More...

const Event *	GetEvent () const

const Event *	GetEvent (const TMVA::Event *ev) const

const Event *	GetEvent (Long64_t ievt) const

const Event *	GetEvent (Long64_t ievt, Types::ETreeType type) const

const Event *	GetTrainingEvent (Long64_t ievt) const

const Event *	GetTestingEvent (Long64_t ievt) const

const std::vector< TMVA::Event * > &	GetEventCollection (Types::ETreeType type)
	returns the event collection (i.e. More...

virtual Bool_t	IsSignalLike ()
	uses a pre-set cut on the MVA output (SetSignalReferenceCut and SetSignalReferenceCutOrientation) for a quick determination if an event would be selected as signal or background More...

virtual Bool_t	IsSignalLike (Double_t mvaVal)
	uses a pre-set cut on the MVA output (SetSignalReferenceCut and SetSignalReferenceCutOrientation) for a quick determination if an event with this mva output value would tbe selected as signal or background More...

Bool_t	HasMVAPdfs () const

virtual void	SetAnalysisType (Types::EAnalysisType type)

Types::EAnalysisType	GetAnalysisType () const

Bool_t	DoRegression () const

Bool_t	DoMulticlass () const

void	DisableWriting (Bool_t setter)

Public Member Functions inherited from TMVA::IMethod
	IMethod ()

virtual	~IMethod ()

Public Member Functions inherited from TMVA::Configurable
	Configurable (const TString &theOption="")

virtual	~Configurable ()
	default destructur More...

virtual void	ParseOptions ()
	options parser More...

void	PrintOptions () const
	prints out the options set in the options string and the defaults More...

const char *	GetConfigName () const

const char *	GetConfigDescription () const

void	SetConfigName (const char *n)

void	SetConfigDescription (const char *d)

template<class T >
OptionBase *	DeclareOptionRef (T &ref, const TString &name, const TString &desc="")

template<class T >
OptionBase *	DeclareOptionRef (T *&ref, Int_t size, const TString &name, const TString &desc="")

template<class T >
void	AddPreDefVal (const T &)

template<class T >
void	AddPreDefVal (const TString &optname, const T &)

void	CheckForUnusedOptions () const
	checks for unused options in option string More...

const TString &	GetOptions () const

void	SetOptions (const TString &s)

void	WriteOptionsToStream (std::ostream &o, const TString &prefix) const
	write options to output stream (e.g. in writing the MVA weight files More...

void	ReadOptionsFromStream (std::istream &istr)
	read option back from the weight file More...

void	AddOptionsXMLTo (void *parent) const
	write options to XML file More...

void	ReadOptionsFromXML (void *node)

void	SetMsgType (EMsgType t)

template<class T >
TMVA::OptionBase *	DeclareOptionRef (T &ref, const TString &name, const TString &desc)

template<class T >
TMVA::OptionBase *	DeclareOptionRef (T *&ref, Int_t size, const TString &name, const TString &desc)

Public Member Functions inherited from TObject
	TObject ()

	TObject (const TObject &object)
	TObject copy ctor. More...

TObject &	operator= (const TObject &rhs)
	TObject assignment operator. More...

virtual	~TObject ()
	TObject destructor. More...

virtual void	AppendPad (Option_t *option="")
	Append graphics object to current pad. More...

virtual void	Browse (TBrowser *b)
	Browse object. May be overridden for another default action. More...

virtual const char *	ClassName () const
	Returns name of class to which the object belongs. More...

virtual void	Clear (Option_t *="")

virtual TObject *	Clone (const char *newname="") const
	Make a clone of an object using the Streamer facility. More...

virtual Int_t	Compare (const TObject *obj) const
	Compare abstract method. More...

virtual void	Copy (TObject &object) const
	Copy this to obj. More...

virtual void	Delete (Option_t *option="")
	Delete this object. More...

virtual Int_t	DistancetoPrimitive (Int_t px, Int_t py)
	Computes distance from point (px,py) to the object. More...

virtual void	Draw (Option_t *option="")
	Default Draw method for all objects. More...

virtual void	DrawClass () const
	Draw class inheritance tree of the class to which this object belongs. More...

virtual TObject *	DrawClone (Option_t *option="") const
	Draw a clone of this object in the current pad. More...

virtual void	Dump () const
	Dump contents of object on stdout. More...

virtual void	Execute (const char method, const char params, Int_t *error=0)
	Execute method on this object with the given parameter string, e.g. More...

virtual void	Execute (TMethod method, TObjArray params, Int_t *error=0)
	Execute method on this object with parameters stored in the TObjArray. More...

virtual void	ExecuteEvent (Int_t event, Int_t px, Int_t py)
	Execute action corresponding to an event at (px,py). More...

virtual TObject *	FindObject (const char *name) const
	Must be redefined in derived classes. More...

virtual TObject *	FindObject (const TObject *obj) const
	Must be redefined in derived classes. More...

virtual Option_t *	GetDrawOption () const
	Get option used by the graphics system to draw this object. More...

virtual UInt_t	GetUniqueID () const
	Return the unique object id. More...

virtual const char *	GetIconName () const
	Returns mime type name of object. More...

virtual Option_t *	GetOption () const

virtual char *	GetObjectInfo (Int_t px, Int_t py) const
	Returns string containing info about the object at position (px,py). More...

virtual const char *	GetTitle () const
	Returns title of object. More...

virtual Bool_t	HandleTimer (TTimer *timer)
	Execute action in response of a timer timing out. More...

virtual ULong_t	Hash () const
	Return hash value for this object. More...

virtual Bool_t	InheritsFrom (const char *classname) const
	Returns kTRUE if object inherits from class "classname". More...

virtual Bool_t	InheritsFrom (const TClass *cl) const
	Returns kTRUE if object inherits from TClass cl. More...

virtual void	Inspect () const
	Dump contents of this object in a graphics canvas. More...

virtual Bool_t	IsFolder () const
	Returns kTRUE in case object contains browsable objects (like containers or lists of other objects). More...

virtual Bool_t	IsEqual (const TObject *obj) const
	Default equal comparison (objects are equal if they have the same address in memory). More...

virtual Bool_t	IsSortable () const

Bool_t	IsOnHeap () const

Bool_t	IsZombie () const

virtual Bool_t	Notify ()
	This method must be overridden to handle object notification. More...

virtual void	ls (Option_t *option="") const
	The ls function lists the contents of a class on stdout. More...

virtual void	Paint (Option_t *option="")
	This method must be overridden if a class wants to paint itself. More...

virtual void	Pop ()
	Pop on object drawn in a pad to the top of the display list. More...

virtual void	Print (Option_t *option="") const
	This method must be overridden when a class wants to print itself. More...

virtual Int_t	Read (const char *name)
	Read contents of object with specified name from the current directory. More...

virtual void	RecursiveRemove (TObject *obj)
	Recursively remove this object from a list. More...

virtual void	SaveAs (const char filename="", Option_t option="") const
	Save this object in the file specified by filename. More...

virtual void	SavePrimitive (std::ostream &out, Option_t *option="")
	Save a primitive as a C++ statement(s) on output stream "out". More...

virtual void	SetDrawOption (Option_t *option="")
	Set drawing option for object. More...

virtual void	SetUniqueID (UInt_t uid)
	Set the unique object id. More...

virtual void	UseCurrentStyle ()
	Set current style settings in this object This function is called when either TCanvas::UseCurrentStyle or TROOT::ForceStyle have been invoked. More...

virtual Int_t	Write (const char *name=0, Int_t option=0, Int_t bufsize=0)
	Write this object to the current directory. More...

virtual Int_t	Write (const char *name=0, Int_t option=0, Int_t bufsize=0) const
	Write this object to the current directory. More...

void *	operator new (size_t sz)

void *	operator new[] (size_t sz)

void *	operator new (size_t sz, void *vp)

void *	operator new[] (size_t sz, void *vp)

void	operator delete (void *ptr)
	Operator delete. More...

void	operator delete[] (void *ptr)
	Operator delete []. More...

void	SetBit (UInt_t f, Bool_t set)
	Set or unset the user status bits as specified in f. More...

void	SetBit (UInt_t f)

void	ResetBit (UInt_t f)

Bool_t	TestBit (UInt_t f) const

Int_t	TestBits (UInt_t f) const

void	InvertBit (UInt_t f)

virtual void	Info (const char method, const char msgfmt,...) const
	Issue info message. More...

virtual void	Warning (const char method, const char msgfmt,...) const
	Issue warning message. More...

virtual void	Error (const char method, const char msgfmt,...) const
	Issue error message. More...

virtual void	SysError (const char method, const char msgfmt,...) const
	Issue system error message. More...

virtual void	Fatal (const char method, const char msgfmt,...) const
	Issue fatal error message. More...

void	AbstractMethod (const char *method) const
	Use this method to implement an "abstract" method that you don't want to leave purely abstract. More...

void	MayNotUse (const char *method) const
	Use this method to signal that a method (defined in a base class) may not be called in a derived class (in principle against good design since a child class should not provide less functionality than its parent, however, sometimes it is necessary). More...

void	Obsolete (const char method, const char asOfVers, const char *removedFromVers) const
	Use this method to declare a method obsolete. More...

Public Member Functions inherited from TMVA::IFitterTarget
	IFitterTarget ()

virtual	~IFitterTarget ()

virtual void	ProgressNotifier (TString, TString)

Public Member Functions inherited from TMVA::ConvergenceTest
	ConvergenceTest ()
	constructor More...

	~ConvergenceTest ()
	destructor More...

void	SetConvergenceParameters (Int_t steps, Double_t improvement)

void	SetCurrentValue (Float_t value)

Float_t	GetCurrentValue ()

void	ResetConvergenceCounter ()

Bool_t	HasConverged (Bool_t withinConvergenceBand=kFALSE)
	gives back true if the last "steps" steps have lead to an improvement of the "fitness" of the "individuals" of at least "improvement" More...

Float_t	Progress ()
	returns a float from 0 (just started) to 1 (finished) More...

Float_t	SpeedControl (UInt_t ofSteps)
	this function provides the ability to change the learning rate according to the success of the last generations. More...

Protected Member Functions
void	MakeClassSpecific (std::ostream &, const TString &) const
	write specific classifier response More...

void	GetHelpMessage () const
	get help message text More...

Protected Member Functions inherited from TMVA::MethodANNBase
std::vector< Int_t > *	ParseLayoutString (TString layerSpec)
	parse layout specification string and return a vector, each entry containing the number of neurons to go in each successive layer More...

virtual void	BuildNetwork (std::vector< Int_t > layout, std::vector< Double_t > weights=NULL, Bool_t fromFile=kFALSE)
	build network given a layout (number of neurons in each layer) and optional weights array More...

void	ForceNetworkInputs (const Event *ev, Int_t ignoreIndex=-1)
	force the input values of the input neurons force the value for each input neuron More...

Double_t	GetNetworkOutput ()

void	PrintMessage (TString message, Bool_t force=kFALSE) const
	print messages, turn off printing by setting verbose and debug flag appropriately More...

void	ForceNetworkCalculations ()
	calculate input values to each neuron More...

void	WaitForKeyboard ()
	wait for keyboard input, for debugging More...

Int_t	NumCycles ()

TNeuron *	GetInputNeuron (Int_t index)

TNeuron *	GetOutputNeuron (Int_t index=0)

void	CreateWeightMonitoringHists (const TString &bulkname, std::vector< TH1 * > *hv=0) const

Protected Member Functions inherited from TMVA::MethodBase
void	NoErrorCalc (Double_t const err, Double_t const errUpper)

virtual void	ReadWeightsFromStream (TFile &)

void	SetWeightFileName (TString)
	set the weight file name (depreciated) More...

const TString &	GetWeightFileDir () const

void	SetWeightFileDir (TString fileDir)
	set directory of weight file More...

Bool_t	IsNormalised () const

void	SetNormalised (Bool_t norm)

Bool_t	Verbose () const

Bool_t	Help () const

const TString &	GetInternalVarName (Int_t ivar) const

const TString &	GetOriginalVarName (Int_t ivar) const

Bool_t	HasTrainingTree () const

virtual void	MakeClassSpecificHeader (std::ostream &, const TString &="") const

void	Statistics (Types::ETreeType treeType, const TString &theVarName, Double_t &, Double_t &, Double_t &, Double_t &, Double_t &, Double_t &)
	calculates rms,mean, xmin, xmax of the event variable this can be either done for the variables as they are or for normalised variables (in the range of 0-1) if "norm" is set to kTRUE More...

Bool_t	TxtWeightsOnly () const

Bool_t	IsConstructedFromWeightFile () const

Bool_t	IgnoreEventsWithNegWeightsInTraining () const

Protected Member Functions inherited from TMVA::Configurable
Bool_t	LooseOptionCheckingEnabled () const

void	EnableLooseOptions (Bool_t b=kTRUE)

void	WriteOptionsReferenceToFile ()
	write complete options to output stream More...

void	ResetSetFlag ()
	resets the IsSet falg for all declare options to be called before options are read from stream More...

const TString &	GetReferenceFile () const

MsgLogger &	Log () const

Protected Member Functions inherited from TObject
void	MakeZombie ()

virtual void	DoError (int level, const char location, const char fmt, va_list va) const
	Interface to ErrorHandler (protected). More...

Private Member Functions
void	DeclareOptions ()
	define the options (their key words) that can be set in the option string know options: TrainingMethod <string> Training method available values are: BP Back-Propagation <default> GA Genetic Algorithm (takes a LONG time) More...

void	ProcessOptions ()
	process user options More...

void	Train (Int_t nEpochs)

void	Init ()
	default initializations More...

void	InitializeLearningRates ()
	initialize learning rates of synapses, used only by backpropagation More...

Double_t	CalculateEstimator (Types::ETreeType treeType=Types::kTraining, Int_t iEpoch=-1)
	calculate the estimator that training is attempting to minimize More...

void	BFGSMinimize (Int_t nEpochs)
	train network with BFGS algorithm More...

void	SetGammaDelta (TMatrixD &Gamma, TMatrixD &Delta, std::vector< Double_t > &Buffer)

void	SteepestDir (TMatrixD &Dir)

Bool_t	GetHessian (TMatrixD &Hessian, TMatrixD &Gamma, TMatrixD &Delta)

void	SetDir (TMatrixD &Hessian, TMatrixD &Dir)

Double_t	DerivDir (TMatrixD &Dir)

Bool_t	LineSearch (TMatrixD &Dir, std::vector< Double_t > &Buffer, Double_t *dError=0)

void	ComputeDEDw ()

void	SimulateEvent (const Event *ev)

void	SetDirWeights (std::vector< Double_t > &Origin, TMatrixD &Dir, Double_t alpha)

Double_t	GetError ()

Double_t	GetMSEErr (const Event *ev, UInt_t index=0)

Double_t	GetCEErr (const Event *ev, UInt_t index=0)

void	BackPropagationMinimize (Int_t nEpochs)
	minimize estimator / train network with backpropagation algorithm More...

void	TrainOneEpoch ()
	train network over a single epoch/cyle of events More...

void	Shuffle (Int_t *index, Int_t n)
	Input: index: the array to shuffle n: the size of the array Output: index: the shuffled indexes This method is used for sequential training. More...

void	DecaySynapseWeights (Bool_t lateEpoch)
	decay synapse weights in last 10 epochs, lower learning rate even more to find a good minimum More...

void	TrainOneEvent (Int_t ievt)
	train network over a single event this uses the new event model More...

Double_t	GetDesiredOutput (const Event *ev)
	get the desired output of this event More...

void	UpdateNetwork (Double_t desired, Double_t eventWeight=1.0)
	update the network based on how closely the output matched the desired output More...

void	UpdateNetwork (const std::vector< Float_t > &desired, Double_t eventWeight=1.0)
	update the network based on how closely the output matched the desired output More...

void	CalculateNeuronDeltas ()
	have each neuron calculate its delta by backpropagation More...

void	UpdateSynapses ()
	update synapse error fields and adjust the weights (if in sequential mode) More...

void	AdjustSynapseWeights ()
	just adjust the synapse weights (should be called in batch mode) More...

void	TrainOneEventFast (Int_t ievt, Float_t *&branchVar, Int_t &type)
	fast per-event training More...

void	GeneticMinimize ()
	create genetics class similar to GeneticCut give it vector of parameter ranges (parameters = weights) link fitness function of this class to ComputeEstimator instantiate GA (see MethodCuts) run it then this should exist for GA, Minuit and random sampling More...

void	GetApproxInvHessian (TMatrixD &InvHessian, bool regulate=true)

void	UpdateRegulators ()

void	UpdatePriors ()

Private Attributes
bool	fUseRegulator

bool	fCalculateErrors

Double_t	fPrior

std::vector< Double_t >	fPriorDev

Int_t	fUpdateLimit

ETrainingMethod	fTrainingMethod

TString	fTrainMethodS

Float_t	fSamplingFraction

Float_t	fSamplingEpoch

Float_t	fSamplingWeight

Bool_t	fSamplingTraining

Bool_t	fSamplingTesting

Double_t	fLastAlpha

Double_t	fTau

Int_t	fResetStep

Double_t	fLearnRate

Double_t	fDecayRate

EBPTrainingMode	fBPMode

TString	fBpModeS

Int_t	fBatchSize

Int_t	fTestRate

Bool_t	fEpochMon

Int_t	fGA_nsteps

Int_t	fGA_preCalc

Int_t	fGA_SC_steps

Int_t	fGA_SC_rate

Double_t	fGA_SC_factor

std::vector< std::pair< Float_t, Float_t > > *	fDeviationsFromTargets

Float_t	fWeightRange

Static Private Attributes
static const Int_t	fgPRINT_ESTIMATOR_INC = 10

static const Bool_t	fgPRINT_SEQ = kFALSE

static const Bool_t	fgPRINT_BATCH = kFALSE

Additional Inherited Members
Static Public Member Functions inherited from TObject
static Long_t	GetDtorOnly ()
	Return destructor only flag. More...

static void	SetDtorOnly (void *obj)
	Set destructor only flag. More...

static Bool_t	GetObjectStat ()
	Get status of object stat flag. More...

static void	SetObjectStat (Bool_t stat)
	Turn on/off tracking of objects in the TObjectTable. More...

Public Attributes inherited from TMVA::MethodBase
const Event *	fTmpEvent

Bool_t	fSetupCompleted

Static Protected Member Functions inherited from TMVA::MethodBase
static MethodBase *	GetThisBase ()
	return a pointer the base class of this method More...

Protected Attributes inherited from TMVA::MethodANNBase
TObjArray *	fNetwork

TObjArray *	fSynapses

TActivation *	fActivation

TActivation *	fOutput

TActivation *	fIdentity

TRandom3 *	frgen

TNeuronInput *	fInputCalculator

std::vector< Int_t >	fRegulatorIdx

std::vector< Double_t >	fRegulators

EEstimator	fEstimator

TString	fEstimatorS

TH1F *	fEstimatorHistTrain

TH1F *	fEstimatorHistTest

std::vector< TH1 * >	fEpochMonHistS

std::vector< TH1 * >	fEpochMonHistB

std::vector< TH1 * >	fEpochMonHistW

TMatrixD	fInvHessian

bool	fUseRegulator

Int_t	fRandomSeed

Int_t	fNcycles

TString	fNeuronType

TString	fNeuronInputType

Protected Attributes inherited from TMVA::MethodBase
Ranking *	fRanking

std::vector< TString > *	fInputVars

Int_t	fNbins

Int_t	fNbinsMVAoutput

Int_t	fNbinsH

Types::EAnalysisType	fAnalysisType

std::vector< Float_t > *	fRegressionReturnVal

std::vector< Float_t > *	fMulticlassReturnVal

UInt_t	fSignalClass

UInt_t	fBackgroundClass

Protected Attributes inherited from TMVA::ConvergenceTest
Float_t	fCurrentValue

Float_t	fImprovement
	current value More...

Int_t	fSteps
	minimum improvement which counts as improvement More...

#include <TMVA/MethodMLP.h>

Inheritance diagram for TMVA::MethodMLP:

Collaboration diagram for TMVA::MethodMLP:

Member Enumeration Documentation

enum TMVA::MethodMLP::EBPTrainingMode

Enumerator
kSequential
kBatch

Definition at line 119 of file MethodMLP.h.

enum TMVA::MethodMLP::ETrainingMethod

Enumerator
kBP
kBFGS
kGA

Definition at line 118 of file MethodMLP.h.

Constructor & Destructor Documentation

TMVA::MethodMLP::MethodMLP	(	const TString &	jobName,
		const TString &	methodTitle,
		DataSetInfo &	theData,
		const TString &	theOption,
		TDirectory *	theTargetDir = `0`
	)

TMVA::MethodMLP::MethodMLP	(	DataSetInfo &	theData,
		const TString &	theWeightFile,
		TDirectory *	theTargetDir = `0`
	)

constructor from a weight file

Definition at line 103 of file MethodMLP.cxx.

TMVA::MethodMLP::~MethodMLP ( )

virtual

destructor nothing to be done

Definition at line 127 of file MethodMLP.cxx.

Member Function Documentation

void TMVA::MethodMLP::AdjustSynapseWeights ( )

private

just adjust the synapse weights (should be called in batch mode)

Definition at line 1379 of file MethodMLP.cxx.

void TMVA::MethodMLP::BackPropagationMinimize ( Int_t nEpochs )

private

minimize estimator / train network with backpropagation algorithm

Definition at line 1000 of file MethodMLP.cxx.

void TMVA::MethodMLP::BFGSMinimize ( Int_t nEpochs )

private

train network with BFGS algorithm

Definition at line 459 of file MethodMLP.cxx.

Double_t TMVA::MethodMLP::CalculateEstimator	(	Types::ETreeType	treeType = `Types::kTraining`,
		Int_t	iEpoch = `-1`
	)

private

calculate the estimator that training is attempting to minimize

Definition at line 270 of file MethodMLP.cxx.

void TMVA::MethodMLP::CalculateNeuronDeltas ( )

private

have each neuron calculate its delta by backpropagation

Definition at line 1273 of file MethodMLP.cxx.

void TMVA::MethodMLP::ComputeDEDw ( )

private

Definition at line 660 of file MethodMLP.cxx.

Double_t TMVA::MethodMLP::ComputeEstimator ( std::vector< Double_t > & parameters )

this function is called by GeneticANN for GA optimization

Definition at line 1338 of file MethodMLP.cxx.

void TMVA::MethodMLP::DecaySynapseWeights ( Bool_t lateEpoch )

private

decay synapse weights in last 10 epochs, lower learning rate even more to find a good minimum

Definition at line 1163 of file MethodMLP.cxx.

void TMVA::MethodMLP::DeclareOptions ( )

privatevirtual

define the options (their key words) that can be set in the option string know options: TrainingMethod <string> Training method available values are: BP Back-Propagation <default> GA Genetic Algorithm (takes a LONG time)

LearningRate <float> NN learning rate parameter DecayRate <float> Decay rate for learning parameter TestRate <int> Test for overtraining performed at each #th epochs

BPMode <string> Back-propagation learning mode available values are: sequential <default> batch

BatchSize <int> Batch size: number of events/batch, only set if in Batch Mode, -1 for BatchSize=number_of_events

Reimplemented from TMVA::MethodANNBase.

Definition at line 173 of file MethodMLP.cxx.

Double_t TMVA::MethodMLP::DerivDir ( TMatrixD & Dir )

private

Definition at line 788 of file MethodMLP.cxx.

Double_t TMVA::MethodMLP::EstimatorFunction ( std::vector< Double_t > & parameters )

virtual

interface to the estimate

Implements TMVA::IFitterTarget.

Definition at line 1330 of file MethodMLP.cxx.

void TMVA::MethodMLP::GeneticMinimize ( )

private

create genetics class similar to GeneticCut give it vector of parameter ranges (parameters = weights) link fitness function of this class to ComputeEstimator instantiate GA (see MethodCuts) run it then this should exist for GA, Minuit and random sampling

Definition at line 1301 of file MethodMLP.cxx.

void TMVA::MethodMLP::GetApproxInvHessian	(	TMatrixD &	InvHessian,
		bool	regulate = `true`
	)

private

Definition at line 1453 of file MethodMLP.cxx.

Double_t TMVA::MethodMLP::GetCEErr	(	const Event *	ev,
		UInt_t	index = `0`
	)

private

Definition at line 983 of file MethodMLP.cxx.

Double_t TMVA::MethodMLP::GetDesiredOutput ( const Event * ev )

private

get the desired output of this event

Definition at line 1232 of file MethodMLP.cxx.

Double_t TMVA::MethodMLP::GetError ( )

private

Definition at line 929 of file MethodMLP.cxx.

void TMVA::MethodMLP::GetHelpMessage ( ) const

protectedvirtual

get help message text

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

Implements TMVA::IMethod.

Definition at line 1660 of file MethodMLP.cxx.

Bool_t TMVA::MethodMLP::GetHessian	(	TMatrixD &	Hessian,
		TMatrixD &	Gamma,
		TMatrixD &	Delta
	)

private

Definition at line 750 of file MethodMLP.cxx.

Double_t TMVA::MethodMLP::GetMSEErr	(	const Event *	ev,
		UInt_t	index = `0`
	)

private

Definition at line 966 of file MethodMLP.cxx.

Double_t TMVA::MethodMLP::GetMvaValue	(	Double_t *	err = `0`,
		Double_t *	errUpper = `0`
	)

virtual

get the mva value generated by the NN

Reimplemented from TMVA::MethodANNBase.

Definition at line 1494 of file MethodMLP.cxx.

Bool_t TMVA::MethodMLP::HasAnalysisType	(	Types::EAnalysisType	type,
		UInt_t	numberClasses,
		UInt_t	numberTargets
	)

virtual

MLP can handle classification with 2 classes and regression with one regression-target.

Implements TMVA::IMethod.

Definition at line 134 of file MethodMLP.cxx.

bool TMVA::MethodMLP::HasInverseHessian ( )

inline

Definition at line 121 of file MethodMLP.h.

void TMVA::MethodMLP::Init ( void )

privatevirtual

default initializations

Implements TMVA::MethodBase.

Definition at line 146 of file MethodMLP.cxx.

void TMVA::MethodMLP::InitializeLearningRates ( )

private

initialize learning rates of synapses, used only by backpropagation

Definition at line 256 of file MethodMLP.cxx.

Bool_t TMVA::MethodMLP::LineSearch	(	TMatrixD &	Dir,
		std::vector< Double_t > &	Buffer,
		Double_t *	dError = `0`
	)

private

Definition at line 803 of file MethodMLP.cxx.

void TMVA::MethodMLP::MakeClassSpecific	(	std::ostream &	fout,
		const TString &	className
	)		const

protectedvirtual

write specific classifier response

Reimplemented from TMVA::MethodANNBase.

Definition at line 1649 of file MethodMLP.cxx.

void TMVA::MethodMLP::ProcessOptions ( )

privatevirtual

process user options

Reimplemented from TMVA::MethodANNBase.

Definition at line 225 of file MethodMLP.cxx.

void TMVA::MethodMLP::SetDir	(	TMatrixD &	Hessian,
		TMatrixD &	Dir
	)

private

Definition at line 771 of file MethodMLP.cxx.

void TMVA::MethodMLP::SetDirWeights	(	std::vector< Double_t > &	Origin,
		TMatrixD &	Dir,
		Double_t	alpha
	)

private

Definition at line 913 of file MethodMLP.cxx.

void TMVA::MethodMLP::SetGammaDelta	(	TMatrixD &	Gamma,
		TMatrixD &	Delta,
		std::vector< Double_t > &	Buffer
	)

private

Definition at line 635 of file MethodMLP.cxx.

void TMVA::MethodMLP::Shuffle	(	Int_t *	index,
		Int_t	n
	)

private

Input: index: the array to shuffle n: the size of the array Output: index: the shuffled indexes This method is used for sequential training.

Definition at line 1145 of file MethodMLP.cxx.

void TMVA::MethodMLP::SimulateEvent ( const Event * ev )

private

Definition at line 697 of file MethodMLP.cxx.

void TMVA::MethodMLP::SteepestDir ( TMatrixD & Dir )

private

Definition at line 737 of file MethodMLP.cxx.

void TMVA::MethodMLP::Train ( void )

inlinevirtual

Implements TMVA::MethodANNBase.

Definition at line 112 of file MethodMLP.h.

Referenced by Train().

void TMVA::MethodMLP::Train ( Int_t nEpochs )

private

Definition at line 416 of file MethodMLP.cxx.

void TMVA::MethodMLP::TrainOneEpoch ( )

private

train network over a single epoch/cyle of events

Definition at line 1098 of file MethodMLP.cxx.

void TMVA::MethodMLP::TrainOneEvent ( Int_t ievt )

private

train network over a single event this uses the new event model

Definition at line 1213 of file MethodMLP.cxx.

void TMVA::MethodMLP::TrainOneEventFast	(	Int_t	ievt,
		Float_t *&	branchVar,
		Int_t &	type
	)

private

fast per-event training

Definition at line 1177 of file MethodMLP.cxx.

void TMVA::MethodMLP::UpdateNetwork	(	Double_t	desired,
		Double_t	eventWeight = `1.0`
	)

private

update the network based on how closely the output matched the desired output

Definition at line 1242 of file MethodMLP.cxx.

void TMVA::MethodMLP::UpdateNetwork	(	const std::vector< Float_t > &	desired,
		Double_t	eventWeight = `1.0`
	)

private

update the network based on how closely the output matched the desired output

Definition at line 1258 of file MethodMLP.cxx.

void TMVA::MethodMLP::UpdatePriors ( )

private

Definition at line 1399 of file MethodMLP.cxx.

void TMVA::MethodMLP::UpdateRegulators ( )

private

Definition at line 1413 of file MethodMLP.cxx.

void TMVA::MethodMLP::UpdateSynapses ( )

private

update synapse error fields and adjust the weights (if in sequential mode)

Definition at line 1357 of file MethodMLP.cxx.

Member Data Documentation

Int_t TMVA::MethodMLP::fBatchSize

private

Definition at line 219 of file MethodMLP.h.

EBPTrainingMode TMVA::MethodMLP::fBPMode

private

Definition at line 217 of file MethodMLP.h.

TString TMVA::MethodMLP::fBpModeS

private

Definition at line 218 of file MethodMLP.h.

bool TMVA::MethodMLP::fCalculateErrors

private

Definition at line 192 of file MethodMLP.h.

Referenced by HasInverseHessian().

Double_t TMVA::MethodMLP::fDecayRate

private

Definition at line 216 of file MethodMLP.h.

std::vector<std::pair<Float_t,Float_t> >* TMVA::MethodMLP::fDeviationsFromTargets

private

Definition at line 231 of file MethodMLP.h.

Bool_t TMVA::MethodMLP::fEpochMon

private

Definition at line 221 of file MethodMLP.h.

Int_t TMVA::MethodMLP::fGA_nsteps

private

Definition at line 224 of file MethodMLP.h.

Int_t TMVA::MethodMLP::fGA_preCalc

private

Definition at line 225 of file MethodMLP.h.

Double_t TMVA::MethodMLP::fGA_SC_factor

private

Definition at line 228 of file MethodMLP.h.

Int_t TMVA::MethodMLP::fGA_SC_rate

private

Definition at line 227 of file MethodMLP.h.

Int_t TMVA::MethodMLP::fGA_SC_steps

private

Definition at line 226 of file MethodMLP.h.

const Bool_t TMVA::MethodMLP::fgPRINT_BATCH = kFALSE

staticprivate

Definition at line 244 of file MethodMLP.h.

const Int_t TMVA::MethodMLP::fgPRINT_ESTIMATOR_INC = 10

staticprivate

Definition at line 242 of file MethodMLP.h.

const Bool_t TMVA::MethodMLP::fgPRINT_SEQ = kFALSE

staticprivate

Definition at line 243 of file MethodMLP.h.

Double_t TMVA::MethodMLP::fLastAlpha

private

Definition at line 210 of file MethodMLP.h.

Double_t TMVA::MethodMLP::fLearnRate

private

Definition at line 215 of file MethodMLP.h.

Double_t TMVA::MethodMLP::fPrior

private

Definition at line 193 of file MethodMLP.h.

std::vector<Double_t> TMVA::MethodMLP::fPriorDev

private

Definition at line 194 of file MethodMLP.h.

Int_t TMVA::MethodMLP::fResetStep

private

Definition at line 212 of file MethodMLP.h.

Float_t TMVA::MethodMLP::fSamplingEpoch

private

Definition at line 204 of file MethodMLP.h.

Float_t TMVA::MethodMLP::fSamplingFraction

private

Definition at line 203 of file MethodMLP.h.

Bool_t TMVA::MethodMLP::fSamplingTesting

private

Definition at line 207 of file MethodMLP.h.

Bool_t TMVA::MethodMLP::fSamplingTraining

private

Definition at line 206 of file MethodMLP.h.

Float_t TMVA::MethodMLP::fSamplingWeight

private

Definition at line 205 of file MethodMLP.h.

Double_t TMVA::MethodMLP::fTau

private

Definition at line 211 of file MethodMLP.h.

Int_t TMVA::MethodMLP::fTestRate

private

Definition at line 220 of file MethodMLP.h.

ETrainingMethod TMVA::MethodMLP::fTrainingMethod

private

Definition at line 200 of file MethodMLP.h.

TString TMVA::MethodMLP::fTrainMethodS

private

Definition at line 201 of file MethodMLP.h.

Int_t TMVA::MethodMLP::fUpdateLimit

private

Definition at line 198 of file MethodMLP.h.

bool TMVA::MethodMLP::fUseRegulator

private

Definition at line 191 of file MethodMLP.h.

Float_t TMVA::MethodMLP::fWeightRange

private

Definition at line 233 of file MethodMLP.h.

The documentation for this class was generated from the following files:

tmva/tmva/inc/TMVA/MethodMLP.h
tmva/tmva/src/MethodMLP.cxx

Public Types

Public Member Functions

Protected Member Functions

Private Member Functions

Private Attributes

Static Private Attributes

Additional Inherited Members

Member Enumeration Documentation

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation