TMultiLayerPerceptron Class Reference

This class describes a neural network.

There are facilities to train the network and use the output.

The input layer is made of inactive neurons (returning the optionally normalized input) and output neurons are linear. The type of hidden neurons is free, the default being sigmoids. (One should still try to pass normalized inputs, e.g. between [0.,1])

The basic input is a TTree and two (training and test) TEventLists. Input and output neurons are assigned a value computed for each event with the same possibilities as for TTree::Draw(). Events may be weighted individually or via TTree::SetWeight(). 6 learning methods are available: kStochastic, kBatch, kSteepestDescent, kRibierePolak, kFletcherReeves and kBFGS.

This implementation, written by C. Delaere, is inspired from the mlpfit package from J.Schwindling et al. with some extensions:

• the algorithms are globally the same
• in TMultilayerPerceptron, there is no limitation on the number of layers/neurons, while MLPFIT was limited to 2 hidden layers
• TMultilayerPerceptron allows you to save the network in a root file, and provides more export functionalities
• TMultilayerPerceptron gives more flexibility regarding the normalization of inputs/outputs
• TMultilayerPerceptron provides, thanks to Andrea Bocci, the possibility to use cross-entropy errors, which allows to train a network for pattern classification based on Bayesian posterior probability.

Introduction

Neural Networks are more and more used in various fields for data analysis and classification, both for research and commercial institutions. Some randomly chosen examples are:

• image analysis
• financial movements predictions and analysis
• sales forecast and product shipping optimisation
• in particles physics: mainly for classification tasks (signal over background discrimination)

More than 50% of neural networks are multilayer perceptrons. This implementation of multilayer perceptrons is inspired from the MLPfit package originally written by Jerome Schwindling. MLPfit remains one of the fastest tool for neural networks studies, and this ROOT add-on will not try to compete on that. A clear and flexible Object Oriented implementation has been chosen over a faster but more difficult to maintain code. Nevertheless, the time penalty does not exceed a factor 2.

The MLP

The multilayer perceptron is a simple feed-forward network with the following structure:

It is made of neurons characterized by a bias and weighted links between them (let's call those links synapses). The input neurons receive the inputs, normalize them and forward them to the first hidden layer.

Each neuron in any subsequent layer first computes a linear combination of the outputs of the previous layer. The output of the neuron is then function of that combination with f being linear for output neurons or a sigmoid for hidden layers. This is useful because of two theorems:

1. A linear combination of sigmoids can approximate any continuous function.
2. Trained with output = 1 for the signal and 0 for the background, the approximated function of inputs X is the probability of signal, knowing X.

Learning methods

The aim of all learning methods is to minimize the total error on a set of weighted examples. The error is defined as the sum in quadrature, divided by two, of the error on each individual output neuron. In all methods implemented, one needs to compute the first derivative of that error with respect to the weights. Exploiting the well-known properties of the derivative, especially the derivative of compound functions, one can write:

• for a neuron: product of the local derivative with the weighted sum on the outputs of the derivatives.
• for a synapse: product of the input with the local derivative of the output neuron.

This computation is called back-propagation of the errors. A loop over all examples is called an epoch. Six learning methods are implemented.

Stochastic minimization:

is the most trivial learning method. This is the Robbins-Monro stochastic approximation applied to multilayer perceptrons. The weights are updated after each example according to the formula: \(w_{ij}(t+1) = w_{ij}(t) + \Delta w_{ij}(t)\)

with

\(\Delta w_{ij}(t) = - \eta(d e_p / d w_{ij} + \delta) + \epsilon \Delta w_{ij}(t-1)\)

The parameters for this method are Eta, EtaDecay, Delta and Epsilon.

Steepest descent with fixed step size (batch learning):

It is the same as the stochastic minimization, but the weights are updated after considering all the examples, with the total derivative dEdw. The parameters for this method are Eta, EtaDecay, Delta and Epsilon.

Steepest descent algorithm:

Weights are set to the minimum along the line defined by the gradient. The only parameter for this method is Tau. Lower tau = higher precision = slower search. A value Tau = 3 seems reasonable.

Conjugate gradients with the Polak-Ribiere updating formula:

Weights are set to the minimum along the line defined by the conjugate gradient. Parameters are Tau and Reset, which defines the epochs where the direction is reset to the steepest descent.

Conjugate gradients with the Fletcher-Reeves updating formula:

Weights are set to the minimum along the line defined by the conjugate gradient. Parameters are Tau and Reset, which defines the epochs where the direction is reset to the steepest descent.

Broyden, Fletcher, Goldfarb, Shanno (BFGS) method:

Implies the computation of a NxN matrix computation, but seems more powerful at least for less than 300 weights. Parameters are Tau and Reset, which defines the epochs where the direction is reset to the steepest descent.

How to use it...

TMLP is build from 3 classes: TNeuron, TSynapse and TMultiLayerPerceptron. Only TMultiLayerPerceptron should be used explicitly by the user.

TMultiLayerPerceptron will take examples from a TTree given in the constructor. The network is described by a simple string: The input/output layers are defined by giving the expression for each neuron, separated by comas. Hidden layers are just described by the number of neurons. The layers are separated by colons. In addition, input/output layer formulas can be preceded by '@' (e.g "@out") if one wants to also normalize the data from the TTree. Input and outputs are taken from the TTree given as second argument. Expressions are evaluated as for TTree::Draw(), arrays are expended in distinct neurons, one for each index. This can only be done for fixed-size arrays. If the formula ends with "!", softmax functions are used for the output layer. One defines the training and test datasets by TEventLists.

Example:

TMultiLayerPerceptron("x,y:10:5:f",inputTree);

Both the TTree and the TEventLists can be defined in the constructor, or later with the suited setter method. The lists used for training and test can be defined either explicitly, or via a string containing the formula to be used to define them, exactly as for a TCut.

The learning method is defined using the TMultiLayerPerceptron::SetLearningMethod() . Learning methods are :

• TMultiLayerPerceptron::kStochastic,
• TMultiLayerPerceptron::kBatch,
• TMultiLayerPerceptron::kSteepestDescent,
• TMultiLayerPerceptron::kRibierePolak,
• TMultiLayerPerceptron::kFletcherReeves,
• TMultiLayerPerceptron::kBFGS

A weight can be assigned to events, either in the constructor, either with TMultiLayerPerceptron::SetEventWeight(). In addition, the TTree weight is taken into account.

Finally, one starts the training with TMultiLayerPerceptron::Train(Int_t nepoch, Option_t* options). The first argument is the number of epochs while option is a string that can contain: "text" (simple text output) , "graph" (evoluting graphical training curves), "update=X" (step for the text/graph output update) or "+" (will skip the randomisation and start from the previous values). All combinations are available.

Example:

net.Train(100,"text, graph, update=10");

When the neural net is trained, it can be used directly ( TMultiLayerPerceptron::Evaluate() ) or exported to a standalone C++ code ( TMultiLayerPerceptron::Export() ).

Finally, note that even if this implementation is inspired from the mlpfit code, the feature lists are not exactly matching:

• mlpfit hybrid learning method is not implemented
• output neurons can be normalized, this is not the case for mlpfit
• the neural net is exported in C++, FORTRAN or PYTHON
• the drawResult() method allows a fast check of the learning procedure

In addition, the paw version of mlpfit had additional limitations on the number of neurons, hidden layers and inputs/outputs that does not apply to TMultiLayerPerceptron.

Definition at line 26 of file TMultiLayerPerceptron.h.

Public Types
enum	{ kSingleKey = (1ULL << (0)) , kOverwrite = (1ULL << (1)) , kWriteDelete = (1ULL << (2)) }
enum	{   kIsOnHeap = 0x01000000 , kNotDeleted = 0x02000000 , kZombie = 0x04000000 , kInconsistent = 0x08000000 ,   kBitMask = 0x00ffffff }
enum	EDataSet { kTraining , kTest }
enum	EDeprecatedStatusBits { kObjInCanvas = (1ULL << (3)) }
enum	ELearningMethod {   kStochastic , kBatch , kSteepestDescent , kRibierePolak ,   kFletcherReeves , kBFGS }
enum	EStatusBits {   kCanDelete = (1ULL << (0)) , kMustCleanup = (1ULL << (3)) , kIsReferenced = (1ULL << (4)) , kHasUUID = (1ULL << (5)) ,   kCannotPick = (1ULL << (6)) , kNoContextMenu = (1ULL << (8)) , kInvalidObject = (1ULL << (13)) }

Public Member Functions
	TMultiLayerPerceptron ()
	Default constructor.
	TMultiLayerPerceptron (const char *layout, const char *weight, TTree *data, TEventList *training, TEventList *test, TNeuron::ENeuronType type=TNeuron::kSigmoid, const char *extF="", const char *extD="")
	The network is described by a simple string: The input/output layers are defined by giving the branch names separated by comas.
	TMultiLayerPerceptron (const char *layout, const char *weight, TTree *data=nullptr, const char *training="Entry$%2==0", const char *test="", TNeuron::ENeuronType type=TNeuron::kSigmoid, const char *extF="", const char *extD="")
	The network is described by a simple string: The input/output layers are defined by giving the branch names separated by comas.
	TMultiLayerPerceptron (const char *layout, TTree *data, TEventList *training, TEventList *test, TNeuron::ENeuronType type=TNeuron::kSigmoid, const char *extF="", const char *extD="")
	The network is described by a simple string: The input/output layers are defined by giving the branch names separated by comas.
	TMultiLayerPerceptron (const char *layout, TTree *data=nullptr, const char *training="Entry$%2==0", const char *test="", TNeuron::ENeuronType type=TNeuron::kSigmoid, const char *extF="", const char *extD="")
	The network is described by a simple string: The input/output layers are defined by giving the branch names separated by comas.
	~TMultiLayerPerceptron () override
	Destructor.
void	AbstractMethod (const char *method) const
	Call this function within a function that you don't want to define as purely virtual, in order not to force all users deriving from that class to implement that maybe (on their side) unused function; but at the same time, emit a run-time warning if they try to call it, telling that it is not implemented in the derived class: action must thus be taken on the user side to override it.
virtual void	AppendPad (Option_t *option="")
	Append graphics object to current pad.
virtual void	Browse (TBrowser *b)
	Browse object. May be overridden for another default action.
ULong_t	CheckedHash ()
	Check and record whether this class has a consistent Hash/RecursiveRemove setup (*) and then return the regular Hash value for this object.
virtual const char *	ClassName () const
	Returns name of class to which the object belongs.
virtual void	Clear (Option_t *="")
virtual TObject *	Clone (const char *newname="") const
	Make a clone of an object using the Streamer facility.
virtual Int_t	Compare (const TObject *obj) const
	Compare abstract method.
void	ComputeDEDw () const
	Compute the DEDw = sum on all training events of dedw for each weight normalized by the number of events.
virtual void	Copy (TObject &object) const
	Copy this to obj.
virtual void	Delete (Option_t *option="")
	Delete this object.
virtual Int_t	DistancetoPrimitive (Int_t px, Int_t py)
	Computes distance from point (px,py) to the object.
void	Draw (Option_t *option="") override
	Draws the network structure.
virtual void	DrawClass () const
	Draw class inheritance tree of the class to which this object belongs.
virtual TObject *	DrawClone (Option_t *option="") const
	Draw a clone of this object in the current selected pad with: gROOT->SetSelectedPad(c1).
void	DrawResult (Int_t index=0, Option_t *option="test") const
	Draws the neural net output It produces an histogram with the output for the two datasets.
virtual void	Dump () const
	Dump contents of object on stdout.
Bool_t	DumpWeights (Option_t *filename="-") const
	Dumps the weights to a text file.
virtual void	Error (const char *method, const char *msgfmt,...) const
	Issue error message.
Double_t	Evaluate (Int_t index, Double_t *params) const
	Returns the Neural Net for a given set of input parameters #parameters must equal #input neurons.
virtual void	Execute (const char *method, const char *params, Int_t *error=nullptr)
	Execute method on this object with the given parameter string, e.g.
virtual void	Execute (TMethod *method, TObjArray *params, Int_t *error=nullptr)
	Execute method on this object with parameters stored in the TObjArray.
virtual void	ExecuteEvent (Int_t event, Int_t px, Int_t py)
	Execute action corresponding to an event at (px,py).
void	Export (Option_t *filename="NNfunction", Option_t *language="C++") const
	Exports the NN as a function for any non-ROOT-dependant code Supported languages are: only C++ , FORTRAN and Python (yet) This feature is also useful if you want to plot the NN as a function (TF1 or TF2).
virtual void	Fatal (const char *method, const char *msgfmt,...) const
	Issue fatal error message.
virtual TObject *	FindObject (const char *name) const
	Must be redefined in derived classes.
virtual TObject *	FindObject (const TObject *obj) const
	Must be redefined in derived classes.
Double_t	GetDelta () const
virtual Option_t *	GetDrawOption () const
	Get option used by the graphics system to draw this object.
Double_t	GetEpsilon () const
Double_t	GetError (Int_t event) const
	Error on the output for a given event.
Double_t	GetError (TMultiLayerPerceptron::EDataSet set) const
	Error on the whole dataset.
Double_t	GetEta () const
Double_t	GetEtaDecay () const
virtual const char *	GetIconName () const
	Returns mime type name of object.
TMultiLayerPerceptron::ELearningMethod	GetLearningMethod () const
virtual const char *	GetName () const
	Returns name of object.
virtual char *	GetObjectInfo (Int_t px, Int_t py) const
	Returns string containing info about the object at position (px,py).
virtual Option_t *	GetOption () const
Int_t	GetReset () const
TString	GetStructure () const
Double_t	GetTau () const
virtual const char *	GetTitle () const
	Returns title of object.
TNeuron::ENeuronType	GetType () const
virtual UInt_t	GetUniqueID () const
	Return the unique object id.
virtual Bool_t	HandleTimer (TTimer *timer)
	Execute action in response of a timer timing out.
virtual ULong_t	Hash () const
	Return hash value for this object.
Bool_t	HasInconsistentHash () const
	Return true is the type of this object is known to have an inconsistent setup for Hash and RecursiveRemove (i.e.
virtual void	Info (const char *method, const char *msgfmt,...) const
	Issue info message.
virtual Bool_t	InheritsFrom (const char *classname) const
	Returns kTRUE if object inherits from class "classname".
virtual Bool_t	InheritsFrom (const TClass *cl) const
	Returns kTRUE if object inherits from TClass cl.
virtual void	Inspect () const
	Dump contents of this object in a graphics canvas.
void	InvertBit (UInt_t f)
TClass *	IsA () const override
Bool_t	IsDestructed () const
	IsDestructed.
virtual Bool_t	IsEqual (const TObject *obj) const
	Default equal comparison (objects are equal if they have the same address in memory).
virtual Bool_t	IsFolder () const
	Returns kTRUE in case object contains browsable objects (like containers or lists of other objects).
Bool_t	IsOnHeap () const
virtual Bool_t	IsSortable () const
Bool_t	IsZombie () const
Bool_t	LoadWeights (Option_t *filename="")
	Loads the weights from a text file conforming to the format defined by DumpWeights.
virtual void	ls (Option_t *option="") const
	The ls function lists the contents of a class on stdout.
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).
virtual Bool_t	Notify ()
	This method must be overridden to handle object notification (the base implementation is no-op).
void	Obsolete (const char *method, const char *asOfVers, const char *removedFromVers) const
	Use this method to declare a method obsolete.
void	operator delete (void *, size_t)
	Operator delete for sized deallocation.
void	operator delete (void *ptr)
	Operator delete.
void	operator delete (void *ptr, void *vp)
	Only called by placement new when throwing an exception.
void	operator delete[] (void *, size_t)
	Operator delete [] for sized deallocation.
void	operator delete[] (void *ptr)
	Operator delete [].
void	operator delete[] (void *ptr, void *vp)
	Only called by placement new[] when throwing an exception.
void *	operator new (size_t sz)
void *	operator new (size_t sz, void *vp)
void *	operator new[] (size_t sz)
void *	operator new[] (size_t sz, void *vp)
virtual void	Paint (Option_t *option="")
	This method must be overridden if a class wants to paint itself.
virtual void	Pop ()
	Pop on object drawn in a pad to the top of the display list.
virtual void	Print (Option_t *option="") const
	This method must be overridden when a class wants to print itself.
void	Randomize () const
	Randomize the weights.
virtual Int_t	Read (const char *name)
	Read contents of object with specified name from the current directory.
virtual void	RecursiveRemove (TObject *obj)
	Recursively remove this object from a list.
void	ResetBit (UInt_t f)
Double_t	Result (Int_t event, Int_t index=0) const
	Computes the output for a given event.
virtual void	SaveAs (const char *filename="", Option_t *option="") const
	Save this object in the file specified by filename.
virtual void	SavePrimitive (std::ostream &out, Option_t *option="")
	Save a primitive as a C++ statement(s) on output stream "out".
void	SetBit (UInt_t f)
void	SetBit (UInt_t f, Bool_t set)
	Set or unset the user status bits as specified in f.
void	SetData (TTree *)
	Set the data source.
void	SetDelta (Double_t delta)
	Sets Delta - used in stochastic minimisation (look at the constructor for the complete description of learning methods and parameters).
virtual void	SetDrawOption (Option_t *option="")
	Set drawing option for object.
void	SetEpsilon (Double_t eps)
	Sets Epsilon - used in stochastic minimisation (look at the constructor for the complete description of learning methods and parameters).
void	SetEta (Double_t eta)
	Sets Eta - used in stochastic minimisation (look at the constructor for the complete description of learning methods and parameters).
void	SetEtaDecay (Double_t ed)
	Sets EtaDecay - Eta *= EtaDecay at each epoch (look at the constructor for the complete description of learning methods and parameters).
void	SetEventWeight (const char *)
	Set the event weight.
void	SetLearningMethod (TMultiLayerPerceptron::ELearningMethod method)
	Sets the learning method.
void	SetReset (Int_t reset)
	Sets number of epochs between two resets of the search direction to the steepest descent.
void	SetTau (Double_t tau)
	Sets Tau - used in line search (look at the constructor for the complete description of learning methods and parameters).
void	SetTestDataSet (const char *test)
	Sets the Test dataset.
void	SetTestDataSet (TEventList *test)
	Sets the Test dataset.
void	SetTrainingDataSet (const char *train)
	Sets the Training dataset.
void	SetTrainingDataSet (TEventList *train)
	Sets the Training dataset.
virtual void	SetUniqueID (UInt_t uid)
	Set the unique object id.
void	Streamer (TBuffer &) override
	Stream an object of class TObject.
void	StreamerNVirtual (TBuffer &ClassDef_StreamerNVirtual_b)
virtual void	SysError (const char *method, const char *msgfmt,...) const
	Issue system error message.
Bool_t	TestBit (UInt_t f) const
Int_t	TestBits (UInt_t f) const
void	Train (Int_t nEpoch, Option_t *option="text", Double_t minE=0)
	Train the network.
virtual void	UseCurrentStyle ()
	Set current style settings in this object This function is called when either TCanvas::UseCurrentStyle or TROOT::ForceStyle have been invoked.
virtual void	Warning (const char *method, const char *msgfmt,...) const
	Issue warning message.
virtual Int_t	Write (const char *name=nullptr, Int_t option=0, Int_t bufsize=0)
	Write this object to the current directory.
virtual Int_t	Write (const char *name=nullptr, Int_t option=0, Int_t bufsize=0) const
	Write this object to the current directory.

Static Public Member Functions
static TClass *	Class ()
static const char *	Class_Name ()
static constexpr Version_t	Class_Version ()
static const char *	DeclFileName ()
static Longptr_t	GetDtorOnly ()
	Return destructor only flag.
static Bool_t	GetObjectStat ()
	Get status of object stat flag.
static void	SetDtorOnly (void *obj)
	Set destructor only flag.
static void	SetObjectStat (Bool_t stat)
	Turn on/off tracking of objects in the TObjectTable.

Protected Types
enum	{ kOnlyPrepStep = (1ULL << (3)) }

Protected Member Functions
void	AttachData ()
	Connects the TTree to Neurons in input and output layers.
void	BFGSDir (TMatrixD &, Double_t *)
	Computes the direction for the BFGS algorithm as the product between the Hessian estimate (bfgsh) and the dir.
void	BuildNetwork ()
	Instantiates the network from the description.
void	ConjugateGradientsDir (Double_t *, Double_t)
	Sets the search direction to conjugate gradient direction beta should be:
Double_t	DerivDir (Double_t *)
	scalar product between gradient and direction = derivative along direction
virtual void	DoError (int level, const char *location, const char *fmt, va_list va) const
	Interface to ErrorHandler (protected).
bool	GetBFGSH (TMatrixD &, TMatrixD &, TMatrixD &)
	Computes the hessian matrix using the BFGS update algorithm.
Double_t	GetCrossEntropy () const
	Cross entropy error for a softmax output neuron, for a given event.
Double_t	GetCrossEntropyBinary () const
	Cross entropy error for sigmoid output neurons, for a given event.
void	GetEntry (Int_t) const
	Load an entry into the network.
Double_t	GetSumSquareError () const
	Error on the output for a given event.
Bool_t	LineSearch (Double_t *, Double_t *)
	Search along the line defined by direction.
void	MakeZombie ()
void	MLP_Batch (Double_t *)
	One step for the batch (stochastic) method.
void	MLP_Stochastic (Double_t *)
	One step for the stochastic method buffer should contain the previous dw vector and will be updated.
void	SetGammaDelta (TMatrixD &, TMatrixD &, Double_t *)
	Sets the gamma \((g_{(t+1)}-g_{(t)})\) and delta \((w_{(t+1)}-w_{(t)})\) vectors Gamma is computed here, so ComputeDEDw cannot have been called before, and delta is a direct translation of buffer into a TMatrixD.
void	SteepestDir (Double_t *)
	Sets the search direction to steepest descent.

Static Protected Member Functions
static void	SavePrimitiveConstructor (std::ostream &out, TClass *cl, const char *variable_name, const char *constructor_agrs="", Bool_t empty_line=kTRUE)
	Save object constructor in the output stream "out".
static void	SavePrimitiveDraw (std::ostream &out, const char *variable_name, Option_t *option=nullptr)
	Save invocation of primitive Draw() method Skipped if option contains "nodraw" string.
static TString	SavePrimitiveVector (std::ostream &out, const char *prefix, Int_t len, Double_t *arr, Int_t flag=0)
	Save array in the output stream "out" as vector.

Private Member Functions
	TMultiLayerPerceptron (const TMultiLayerPerceptron &)
void	BuildFirstLayer (TString &)
	Instantiates the neurons in input Inputs are normalised and the type is set to kOff (simple forward of the formula value).
void	BuildHiddenLayers (TString &)
	Builds hidden layers.
void	BuildLastLayer (TString &, Int_t)
	Builds the output layer Neurons are linear combinations of input, by default.
void	BuildOneHiddenLayer (const TString &sNumNodes, Int_t &layer, Int_t &prevStart, Int_t &prevStop, Bool_t lastLayer)
	Builds a hidden layer, updates the number of layers.
void	ExpandStructure ()
	Expand the structure of the first layer.
void	MLP_Line (Double_t *, Double_t *, Double_t)
	Sets the weights to a point along a line Weights are set to [origin + (dist * dir)].
TMultiLayerPerceptron &	operator= (const TMultiLayerPerceptron &)
void	Shuffle (Int_t *, Int_t) const
	Shuffle the Int_t index[n] in input.

Static Private Member Functions
static void	AddToTObjectTable (TObject *)
	Private helper function which will dispatch to TObjectTable::AddObj.

Private Attributes
UInt_t	fBits
	bit field status word
Int_t	fCurrentTree
	! index of the current tree in a chain
Double_t	fCurrentTreeWeight
	! weight of the current tree in a chain
TTree *	fData
	! pointer to the tree used as datasource
Double_t	fDelta
	! Delta - used in stochastic minimisation - Default=0.
Double_t	fEpsilon
	! Epsilon - used in stochastic minimisation - Default=0.
Double_t	fEta
	! Eta - used in stochastic minimisation - Default=0.1
Double_t	fEtaDecay
	! EtaDecay - Eta *= EtaDecay at each epoch - Default=1.
TTreeFormula *	fEventWeight
	! formula representing the event weight
TString	fextD
	String containing the derivative name.
TString	fextF
	String containing the function name.
TObjArray	fFirstLayer
	Collection of the input neurons; subset of fNetwork.
Double_t	fLastAlpha
	! internal parameter used in line search
TObjArray	fLastLayer
	Collection of the output neurons; subset of fNetwork.
ELearningMethod	fLearningMethod
	! The Learning Method
TTreeFormulaManager *	fManager
	! TTreeFormulaManager for the weight and neurons
TObjArray	fNetwork
	Collection of all the neurons in the network.
TNeuron::ENeuronType	fOutType
	Type of output neurons.
Int_t	fReset
	! number of epochs between two resets of the search direction to the steepest descent - Default=50
TString	fStructure
	String containing the network structure.
TObjArray	fSynapses
	Collection of all the synapses in the network.
Double_t	fTau
	! Tau - used in line search - Default=3.
TEventList *	fTest
	! EventList defining the events in the test dataset
Bool_t	fTestOwner
	! internal flag whether one has to delete fTest or not
TEventList *	fTraining
	! EventList defining the events in the training dataset
Bool_t	fTrainingOwner
	! internal flag whether one has to delete fTraining or not
TNeuron::ENeuronType	fType
	Type of hidden neurons.
UInt_t	fUniqueID
	object unique identifier
TString	fWeight
	String containing the event weight.

Static Private Attributes
static Longptr_t	fgDtorOnly = 0
	object for which to call dtor only (i.e. no delete)
static Bool_t	fgObjectStat = kTRUE
	if true keep track of objects in TObjectTable

Friends
class	TMLPAnalyzer

#include <TMultiLayerPerceptron.h>

Inheritance diagram for TMultiLayerPerceptron:

Member Enumeration Documentation

anonymous enum

anonymous enum

protectedinherited

Enumerator

kOnlyPrepStep

Used to request that the class specific implementation of TObject::Write just prepare the objects to be ready to be written but do not actually write them into the TBuffer. This is just for example by TBufferMerger to request that the TTree inside the file calls TTree::FlushBaskets (outside of the merging lock) and TBufferMerger will later ask for the write (inside the merging lock). To take advantage of this feature the class needs to overload TObject::Write and use this enum value accordingly. (See TTree::Write and TObject::Write) Do not use, this feature will be migrate to the Merge function (See TClass and TTree::Merge)

Definition at line 106 of file TObject.h.

anonymous enum

anonymous enum

inherited

Enumerator
kSingleKey	write collection with single key
kOverwrite	overwrite existing object with same name
kWriteDelete	write object, then delete previous key with same name

Definition at line 99 of file TObject.h.

anonymous enum

anonymous enum

inherited

Enumerator
kIsOnHeap	object is on heap
kNotDeleted	object has not been deleted
kZombie	object ctor failed
kInconsistent	class overload Hash but does call RecursiveRemove in destructor
kBitMask

Definition at line 89 of file TObject.h.

EDataSet

enum TMultiLayerPerceptron::EDataSet

Enumerator
kTraining
kTest

Definition at line 32 of file TMultiLayerPerceptron.h.

EDeprecatedStatusBits

enum TObject::EDeprecatedStatusBits

inherited

Enumerator
kObjInCanvas	for backward compatibility only, use kMustCleanup

Definition at line 84 of file TObject.h.

ELearningMethod

enum TMultiLayerPerceptron::ELearningMethod

Enumerator
kStochastic
kBatch
kSteepestDescent
kRibierePolak
kFletcherReeves
kBFGS

Definition at line 30 of file TMultiLayerPerceptron.h.

EStatusBits

enum TObject::EStatusBits

inherited

Enumerator
kCanDelete	if object in a list can be deleted
kMustCleanup	if object destructor must call RecursiveRemove()
kIsReferenced	if object is referenced by a TRef or TRefArray
kHasUUID	if object has a TUUID (its fUniqueID=UUIDNumber)
kCannotPick	if object in a pad cannot be picked
kNoContextMenu	if object does not want context menu
kInvalidObject	if object ctor succeeded but object should not be used

Definition at line 70 of file TObject.h.

Constructor & Destructor Documentation

TMultiLayerPerceptron() [1/6]

TMultiLayerPerceptron::TMultiLayerPerceptron

(

)

Default constructor.

Definition at line 263 of file TMultiLayerPerceptron.cxx.

TMultiLayerPerceptron() [2/6]

TMultiLayerPerceptron::TMultiLayerPerceptron	(	const char *	layout,
		TTree *	data = nullptr,
		const char *	training = "Entry$%2==0",
		const char *	test = "",
		TNeuron::ENeuronType	type = TNeuron::kSigmoid,
		const char *	extF = "",
		const char *	extD = "" )

The network is described by a simple string: The input/output layers are defined by giving the branch names separated by comas.

Hidden layers are just described by the number of neurons. The layers are separated by colons.

Ex: "x,y:10:5:f"

The output can be prepended by '@' if the variable has to be normalized. The output can be followed by '!' to use Softmax neurons for the output layer only.

Ex: "x,y:10:5:c1,c2,c3!"

Input and outputs are taken from the TTree given as second argument. training and test are two cuts (see TTreeFormula) defining events to be used during the neural net training and testing.

Example: "Entry$%2", "(Entry$+1)%2".

Both the TTree and the cut can be defined in the constructor, or later with the suited setter method.

Definition at line 445 of file TMultiLayerPerceptron.cxx.

TMultiLayerPerceptron() [3/6]

TMultiLayerPerceptron::TMultiLayerPerceptron	(	const char *	layout,
		const char *	weight,
		TTree *	data = nullptr,
		const char *	training = "Entry$%2==0",
		const char *	test = "",
		TNeuron::ENeuronType	type = TNeuron::kSigmoid,
		const char *	extF = "",
		const char *	extD = "" )

The network is described by a simple string: The input/output layers are defined by giving the branch names separated by comas.

Hidden layers are just described by the number of neurons. The layers are separated by colons.

Ex: "x,y:10:5:f"

The output can be prepended by '@' if the variable has to be normalized. The output can be followed by '!' to use Softmax neurons for the output layer only.

Ex: "x,y:10:5:c1,c2,c3!"

Input and outputs are taken from the TTree given as second argument. training and test are two cuts (see TTreeFormula) defining events to be used during the neural net training and testing.

Example: "Entry$%2", "(Entry$+1)%2".

Both the TTree and the cut can be defined in the constructor, or later with the suited setter method.

Definition at line 523 of file TMultiLayerPerceptron.cxx.

TMultiLayerPerceptron() [4/6]

TMultiLayerPerceptron::TMultiLayerPerceptron	(	const char *	layout,
		TTree *	data,
		TEventList *	training,
		TEventList *	test,
		TNeuron::ENeuronType	type = TNeuron::kSigmoid,
		const char *	extF = "",
		const char *	extD = "" )

The network is described by a simple string: The input/output layers are defined by giving the branch names separated by comas.

Hidden layers are just described by the number of neurons. The layers are separated by colons.

Ex: "x,y:10:5:f"

The output can be prepended by '@' if the variable has to be normalized. The output can be followed by '!' to use Softmax neurons for the output layer only.

Ex: "x,y:10:5:c1,c2,c3!"

Input and outputs are taken from the TTree given as second argument. training and test are the two TEventLists defining events to be used during the neural net training. Both the TTree and the TEventLists can be defined in the constructor, or later with the suited setter method.

Definition at line 317 of file TMultiLayerPerceptron.cxx.

TMultiLayerPerceptron() [5/6]

TMultiLayerPerceptron::TMultiLayerPerceptron	(	const char *	layout,
		const char *	weight,
		TTree *	data,
		TEventList *	training,
		TEventList *	test,
		TNeuron::ENeuronType	type = TNeuron::kSigmoid,
		const char *	extF = "",
		const char *	extD = "" )

The network is described by a simple string: The input/output layers are defined by giving the branch names separated by comas.

Hidden layers are just described by the number of neurons. The layers are separated by colons.

Ex: "x,y:10:5:f"

The output can be prepended by '@' if the variable has to be normalized. The output can be followed by '!' to use Softmax neurons for the output layer only.

Ex: "x,y:10:5:c1,c2,c3!"

Input and outputs are taken from the TTree given as second argument. training and test are the two TEventLists defining events to be used during the neural net training. Both the TTree and the TEventLists can be defined in the constructor, or later with the suited setter method.

Definition at line 379 of file TMultiLayerPerceptron.cxx.

~TMultiLayerPerceptron()

TMultiLayerPerceptron::~TMultiLayerPerceptron ( )

override

Destructor.

Definition at line 580 of file TMultiLayerPerceptron.cxx.

TMultiLayerPerceptron() [6/6]

TMultiLayerPerceptron::TMultiLayerPerceptron ( const TMultiLayerPerceptron & )

private

Member Function Documentation

AbstractMethod()

void TObject::AbstractMethod ( const char * method ) const

inherited

Call this function within a function that you don't want to define as purely virtual, in order not to force all users deriving from that class to implement that maybe (on their side) unused function; but at the same time, emit a run-time warning if they try to call it, telling that it is not implemented in the derived class: action must thus be taken on the user side to override it.

In other word, this method acts as a "runtime purely virtual" warning instead of a "compiler purely virtual" error.

Warning

This interface is a legacy function that is no longer recommended to be used by new development code.

Note

The name "AbstractMethod" does not imply that it's an abstract method in the strict C++ sense.

Definition at line 1149 of file TObject.cxx.

AddToTObjectTable()

void TObject::AddToTObjectTable ( TObject * op )

staticprivateinherited

Private helper function which will dispatch to TObjectTable::AddObj.

Included here to avoid circular dependency between header files.

Definition at line 195 of file TObject.cxx.

AppendPad()

void TObject::AppendPad ( Option_t * option = "" )

virtualinherited

Append graphics object to current pad.

In case no current pad is set yet, create a default canvas with the name "c1".

Definition at line 204 of file TObject.cxx.

AttachData()

void TMultiLayerPerceptron::AttachData ( )

protected

Connects the TTree to Neurons in input and output layers.

The formulas associated to each neuron are created and reported to the network formula manager. By default, the branch is not normalised since this would degrade performance for classification jobs. Normalisation can be requested by putting '@' in front of the formula.

Definition at line 1265 of file TMultiLayerPerceptron.cxx.

BFGSDir()

void TMultiLayerPerceptron::BFGSDir ( TMatrixD & bfgsh, Double_t * dir )

protected

Computes the direction for the BFGS algorithm as the product between the Hessian estimate (bfgsh) and the dir.

Definition at line 2493 of file TMultiLayerPerceptron.cxx.

Browse()

void TObject::Browse ( TBrowser * b )

virtualinherited

Browse object. May be overridden for another default action.

Reimplemented in RooPlot, ROOT::Experimental::XRooFit::xRooNode, ROOT::Internal::THnBaseBrowsable, TApplicationRemote, TASImage, TAxis3D, TBaseClass, TBranch, TBranchClones, TBranchElement, TBranchObject, TBranchSTL, TBrowserObject, TCanvas, TChain, TClass, TCollection, TCollectionPropertyBrowsable, TDatabasePDG, TDirectory, TDirectoryFile, TEfficiency, TF1, TFolder, TGenerator, TGeoManager, TGeometry, TGeoNode, TGeoOverlap, TGeoTrack, TGeoVolume, TGraph2D, TGraph, TH1, THbookBranch, THbookFile, THbookKey, THnBase, THStack, TKey, TKeyMapFile, TLeaf, TMacro, TMapFile, TMultiDimFit, TMultiGraph, TNode, TNtuple, TNtupleD, TPad, TPair, TParticleClassPDG, TPrincipal, TRecorder, TRemoteObject, TROOT, TRootIconList, TSPlot, TStyle, TSystemDirectory, TSystemFile, TTask, TTree, TTreePerfStats, and TVirtualBranchBrowsable.

Definition at line 218 of file TObject.cxx.

BuildFirstLayer()

void TMultiLayerPerceptron::BuildFirstLayer ( TString & input )

private

Instantiates the neurons in input Inputs are normalised and the type is set to kOff (simple forward of the formula value).

Definition at line 1400 of file TMultiLayerPerceptron.cxx.

BuildHiddenLayers()

void TMultiLayerPerceptron::BuildHiddenLayers ( TString & hidden )

private

Builds hidden layers.

Definition at line 1418 of file TMultiLayerPerceptron.cxx.

BuildLastLayer()

void TMultiLayerPerceptron::BuildLastLayer ( TString & output, Int_t prev )

private

Builds the output layer Neurons are linear combinations of input, by default.

If the structure ends with "!", neurons are set up for classification, ie. with a sigmoid (1 neuron) or softmax (more neurons) activation function.

Definition at line 1482 of file TMultiLayerPerceptron.cxx.

BuildNetwork()

void TMultiLayerPerceptron::BuildNetwork ( )

protected

Instantiates the network from the description.

Definition at line 1369 of file TMultiLayerPerceptron.cxx.

BuildOneHiddenLayer()

void TMultiLayerPerceptron::BuildOneHiddenLayer ( const TString & sNumNodes, Int_t & layer, Int_t & prevStart, Int_t & prevStop, Bool_t lastLayer )

private

Builds a hidden layer, updates the number of layers.

Definition at line 1437 of file TMultiLayerPerceptron.cxx.

CheckedHash()

ULong_t TObject::CheckedHash ( )

inlineinherited

Check and record whether this class has a consistent Hash/RecursiveRemove setup (*) and then return the regular Hash value for this object.

The intent is for this routine to be called instead of directly calling the function Hash during "insert" operations. See TObject::HasInconsistenTObjectHash();

(*) The setup is consistent when all classes in the class hierarchy that overload TObject::Hash do call ROOT::CallRecursiveRemoveIfNeeded in their destructor. i.e. it is safe to call the Hash virtual function during the RecursiveRemove operation.

Definition at line 332 of file TObject.h.

Class()

TClass * TMultiLayerPerceptron::Class ( )

static

Returns

TClass describing this class

Class_Name()

const char * TMultiLayerPerceptron::Class_Name ( )

static

Returns

Name of this class

Class_Version()

constexpr Version_t TMultiLayerPerceptron::Class_Version ( )

inlinestaticconstexpr

Returns

Version of this class

Definition at line 151 of file TMultiLayerPerceptron.h.

ClassName()

const char * TObject::ClassName ( ) const

virtualinherited

Returns name of class to which the object belongs.

Definition at line 227 of file TObject.cxx.

Clear()

virtual void TObject::Clear ( Option_t * = "" )

inlinevirtualinherited

Reimplemented in JetEvent, RooLinkedList, ROOT::TSchemaRule, ROOT::v5::TFormula, TBackCompFitter, TBits, TBranchRef, TBtree, TCanvas, TClonesArray, TCollection, TDictAttributeMap, TDirectory, TEventList, TFitter, TFolder, TFormula, TFumili, TGeoCombiTrans, TGeoGenTrans, TGeoHMatrix, TGeoRotation, TGHtml, TGraph2D, TGTextEdit, TGTextEntry, TGTextView, TGView, THashList, THashTable, TLegend, TLinearFitter, TList, TListOfDataMembers, TListOfEnums, TListOfEnumsWithLock, TListOfFunctions, TListOfFunctionTemplates, TMap, TMatrixT< Element >, TMatrixT< AReal >, TMatrixT< Double_t >, TMatrixT< Float_t >, TMatrixTBase< Element >, TMatrixTBase< Double_t >, TMatrixTBase< Float_t >, TMatrixTSparse< Element >, TMatrixTSparse< Double_t >, TMatrixTSparse< Float_t >, TMatrixTSym< Element >, TMatrixTSym< Double_t >, TMatrixTSym< Float_t >, TMrbSubevent_Caen, TMultiDimFit, TMVA::MinuitWrapper, TMVA::ResultsClassification, TMVA::ResultsMulticlass, TMVA::ResultsRegression, TNamed, TNotifyLinkBase, TObjArray, TOrdCollection, TPad, TPaveText, TPrincipal, TProcessID, TRefArray, TRefTable, TStreamerInfo, TTask, TUsrHitBuffer, TVectorT< Element >, TVectorT< Double_t >, TVectorT< Float_t >, TViewPubDataMembers, TViewPubFunctions, TVirtualFitter, TVirtualPad, and TVirtualStreamerInfo.

Definition at line 127 of file TObject.h.

Clone()

TObject * TObject::Clone ( const char * newname = "" ) const

virtualinherited

Make a clone of an object using the Streamer facility.

If the object derives from TNamed, this function is called by TNamed::Clone. TNamed::Clone uses the optional argument to set a new name to the newly created object.

If the object class has a DirectoryAutoAdd function, it will be called at the end of the function with the parameter gDirectory. This usually means that the object will be appended to the current ROOT directory.

Reimplemented in RooAbsArg, RooAbsBinning, RooAbsCollection, RooAbsStudy, RooCatType, RooCmdArg, RooDataHist, RooDataSet, RooFitResult, RooLinkedList, RooStats::HypoTestResult, RooStats::ModelConfig, RooStudyPackage, RooTemplateProxy< T >, RooTemplateProxy< const RooHistFunc >, RooTemplateProxy< RooAbsCategory >, RooTemplateProxy< RooAbsPdf >, RooTemplateProxy< RooAbsReal >, RooTemplateProxy< RooAbsRealLValue >, RooTemplateProxy< RooMultiCategory >, RooTemplateProxy< RooRealVar >, RooWorkspace, TASImage, TChainIndex, TClass, TCollection, TF1, TFunction, TFunctionTemplate, TH1, TImage, TMethod, TMethodCall, TMinuit, TMVA::MinuitWrapper, TNamed, TStreamerInfo, and TTreeIndex.

Definition at line 243 of file TObject.cxx.

Compare()

Int_t TObject::Compare ( const TObject * obj ) const

virtualinherited

Compare abstract method.

Must be overridden if a class wants to be able to compare itself with other objects. Must return -1 if this is smaller than obj, 0 if objects are equal and 1 if this is larger than obj.

Reimplemented in RooAbsArg, RooDouble, TCollection, TEnvRec, TFileInfo, TGeoBranchArray, TGeoOverlap, TGFSFrameElement, TGLBFrameElement, TNamed, TObjString, TParameter< AParamType >, TParameter< Long64_t >, TStructNode, TStructNodeProperty, and TUrl.

Definition at line 258 of file TObject.cxx.

ComputeDEDw()

void TMultiLayerPerceptron::ComputeDEDw

(

)

const

Compute the DEDw = sum on all training events of dedw for each weight normalized by the number of events.

Definition at line 1162 of file TMultiLayerPerceptron.cxx.

ConjugateGradientsDir()

void TMultiLayerPerceptron::ConjugateGradientsDir ( Double_t * dir, Double_t beta )

protected

Sets the search direction to conjugate gradient direction beta should be:

\(||g_{(t+1)}||^2 / ||g_{(t)}||^2\) (Fletcher-Reeves)

\(g_{(t+1)} (g_{(t+1)}-g_{(t)}) / ||g_{(t)}||^2\) (Ribiere-Polak)

Definition at line 2378 of file TMultiLayerPerceptron.cxx.

Copy()

void TObject::Copy ( TObject & object ) const

virtualinherited

Copy this to obj.

Reimplemented in ROOT::v5::TFormula, TArc, TArrow, TAxis3D, TAxis, TBox, TColor, TCrown, TDirectory, TDirectoryFile, TEllipse, TF12, TF1, TF1AbsComposition, TF1Convolution, TF1NormSum, TF2, TF3, TFile, TFolder, TFormula, TFrame, TGTextEdit, TGTextView, TH1, TH1C, TH1D, TH1F, TH1I, TH1L, TH1S, TH2, TH2C, TH2D, TH2F, TH2I, TH2L, TH2Poly, TH2S, TH3, TH3C, TH3D, TH3F, TH3I, TH3L, TH3S, THelix, TLatex, TLegend, TLegendEntry, TLine, TMarker, TMathText, TNamed, TPaletteAxis, TPave, TPaveClass, TPaveLabel, TPieSlice, TPolyLine3D, TPolyLine, TPolyMarker3D, TPolyMarker, TProfile2D, TProfile3D, TProfile, TStyle, TSystemDirectory, TSystemFile, TText, TWbox, and TXTRU.

Definition at line 159 of file TObject.cxx.

DeclFileName()

const char * TMultiLayerPerceptron::DeclFileName ( )

inlinestatic

Returns

Name of the file containing the class declaration

Definition at line 151 of file TMultiLayerPerceptron.h.

Delete()

void TObject::Delete ( Option_t * option = "" )

virtualinherited

Delete this object.

Typically called as a command via the interpreter. Normally use "delete" operator when object has been allocated on the heap.

Reimplemented in RooLinkedList, TAxis, TBtree, TCanvas, TClonesArray, TCollection, TDirectory, TDirectoryFile, TExMap, TFile, TGFrame, TGItemContext, TGTextEdit, THashList, THashTable, TKey, TKeySQL, TKeyXML, TList, TListOfDataMembers, TListOfEnums, TListOfEnumsWithLock, TListOfFunctions, TListOfFunctionTemplates, TMap, TMVA::Results, TObjArray, TObjectTable, TOrdCollection, TProtoClass, TQCommand, TRefArray, TSystemDirectory, TSystemFile, TThread, TTree, TTreeViewer, TViewPubDataMembers, and TViewPubFunctions.

Definition at line 268 of file TObject.cxx.

DerivDir()

Double_t TMultiLayerPerceptron::DerivDir ( Double_t * dir )

protected

scalar product between gradient and direction = derivative along direction

Definition at line 2469 of file TMultiLayerPerceptron.cxx.

DistancetoPrimitive()

Int_t TObject::DistancetoPrimitive ( Int_t px, Int_t py )

virtualinherited

Computes distance from point (px,py) to the object.

This member function must be implemented for each graphics primitive. This default function returns a big number (999999).

Reimplemented in TASImage, TAxis3D, TAxis, TBox, TBRIK, TColorWheel, TCrown, TCurlyArc, TCurlyLine, TDiamond, TEfficiency, TEllipse, TF1, TF2, TF3, TFileDrawMap, TGenerator, TGeoBBox, TGeoCompositeShape, TGeoCone, TGeoConeSeg, TGeoEltu, TGeoHalfSpace, TGeoHype, TGeoNode, TGeoOverlap, TGeoParaboloid, TGeoPcon, TGeoPgon, TGeoScaledShape, TGeoShape, TGeoShapeAssembly, TGeoSphere, TGeoTessellated, TGeoTorus, TGeoTrack, TGeoTube, TGeoTubeSeg, TGeoVGShape, TGeoVolume, TGeoXtru, TGL5DDataSet, TGLHistPainter, TGLParametricEquation, TGLScenePad, TGLTH3Composition, TGLViewer, TGraph2D, TGraph, TGraphEdge, TGraphNode, TGraphPolargram, TH1, THistPainter, THStack, TLine, TMarker3DBox, TMarker, TMultiGraph, TNode, TPad, TPaletteAxis, TParallelCoord, TParallelCoordRange, TParallelCoordVar, TParticle, TPave, TPCON, TPie, TPieSlice, TPoints3DABC, TPolyLine3D, TPolyLine, TPolyMarker3D, TPolyMarker, TPrimary, TScatter2D, TScatter, TSPHE, TSpider, TSpline, TStyle, TText, TTreePerfStats, TTUBE, TTUBS, TVirtualHistPainter, and TXTRU.

Definition at line 284 of file TObject.cxx.

DoError()

void TObject::DoError ( int level, const char * location, const char * fmt, va_list va ) const

protectedvirtualinherited

Interface to ErrorHandler (protected).

Reimplemented in TThread, and TTreeViewer.

Definition at line 1059 of file TObject.cxx.

Draw()

void TMultiLayerPerceptron::Draw ( Option_t * option = "" )

overridevirtual

Draws the network structure.

Neurons are depicted by a blue disk, and synapses by lines connecting neurons. The line width is proportional to the weight.

Reimplemented from TObject.

Definition at line 2523 of file TMultiLayerPerceptron.cxx.

DrawClass()

void TObject::DrawClass ( ) const

virtualinherited

Draw class inheritance tree of the class to which this object belongs.

If a class B inherits from a class A, description of B is drawn on the right side of description of A. Member functions overridden by B are shown in class A with a blue line crossing-out the corresponding member function. The following picture is the class inheritance tree of class TPaveLabel:

Reimplemented in TGFrame, TSystemDirectory, and TSystemFile.

Definition at line 308 of file TObject.cxx.

DrawClone()

TObject * TObject::DrawClone ( Option_t * option = "" ) const

virtualinherited

Draw a clone of this object in the current selected pad with: gROOT->SetSelectedPad(c1).

If pad was not selected - gPad will be used.

Note

For histograms, use the more specialised TH1::DrawCopy().

Reimplemented in TAxis, TCanvas, TGFrame, TSystemDirectory, and TSystemFile.

Definition at line 319 of file TObject.cxx.

DrawResult()

void TMultiLayerPerceptron::DrawResult	(	Int_t	index = 0,
		Option_t *	option = "test" ) const

Draws the neural net output It produces an histogram with the output for the two datasets.

Index is the number of the desired output neuron. "option" can contain:

• test or train to select a dataset
• comp to produce a X-Y comparison plot
• nocanv to not create a new TCanvas for the plot

Definition at line 1532 of file TMultiLayerPerceptron.cxx.

Dump()

void TObject::Dump ( ) const

virtualinherited

Dump contents of object on stdout.

Using the information in the object dictionary (class TClass) each data member is interpreted. If a data member is a pointer, the pointer value is printed

The following output is the Dump of a TArrow object:

fAngle                   0           Arrow opening angle (degrees)
fArrowSize               0.2         Arrow Size
fOption.*fData
fX1                      0.1         X of 1st point
fY1                      0.15        Y of 1st point
fX2                      0.67        X of 2nd point
fY2                      0.83        Y of 2nd point
fUniqueID                0           object unique identifier
fBits                    50331648    bit field status word
fLineColor               1           line color
fLineStyle               1           line style
fLineWidth               1           line width
fFillColor               19          fill area color
fFillStyle               1001        fill area style

Reimplemented in TClass, TCollection, TGFrame, TGPack, and TSystemFile.

Definition at line 367 of file TObject.cxx.

DumpWeights()

Bool_t TMultiLayerPerceptron::DumpWeights

(

Option_t *

filename = "-"

)

const

Dumps the weights to a text file.

Set filename to "-" (default) to dump to the standard output

Definition at line 1606 of file TMultiLayerPerceptron.cxx.

Error()

void TObject::Error ( const char * location, const char * fmt, ... ) const

virtualinherited

Issue error message.

Use "location" to specify the method where the error occurred. Accepts standard printf formatting arguments.

Reimplemented in TFitResult.

Definition at line 1098 of file TObject.cxx.

Evaluate()

Double_t TMultiLayerPerceptron::Evaluate	(	Int_t	index,
		Double_t *	params ) const

Returns the Neural Net for a given set of input parameters #parameters must equal #input neurons.

Definition at line 1712 of file TMultiLayerPerceptron.cxx.

Execute() [1/2]

void TObject::Execute ( const char * method, const char * params, Int_t * error = nullptr )

virtualinherited

Execute method on this object with the given parameter string, e.g.

"3.14,1,\"text\"".

Reimplemented in ROOT::R::TRInterface, TCling, TContextMenu, TInterpreter, and TMethodCall.

Definition at line 378 of file TObject.cxx.

Execute() [2/2]

void TObject::Execute ( TMethod * method, TObjArray * params, Int_t * error = nullptr )

virtualinherited

Execute method on this object with parameters stored in the TObjArray.

The TObjArray should contain an argv vector like:

argv[0] ... argv[n] = the list of TObjString parameters

Reimplemented in ROOT::R::TRInterface, TCling, TContextMenu, TInterpreter, and TMethodCall.

Definition at line 398 of file TObject.cxx.

ExecuteEvent()

void TObject::ExecuteEvent ( Int_t event, Int_t px, Int_t py )

virtualinherited

Execute action corresponding to an event at (px,py).

This method must be overridden if an object can react to graphics events.

Reimplemented in TASImage, TASPaletteEditor::LimitLine, TAxis3D, TAxis, TBox, TButton, TCanvas, TCrown, TCurlyArc, TCurlyLine, TDiamond, TEfficiency, TEllipse, TF1, TF2, TF3, TFrame, TGenerator, TGeoManager, TGeoNode, TGeoOverlap, TGeoShape, TGeoTrack, TGeoVolume, TGL5DDataSet, TGLEventHandler, TGLHistPainter, TGLParametricEquation, TGLScenePad, TGLTH3Composition, TGLViewer, TGraph2D, TGraph, TGraphEdge, TGraphNode, TGraphPolargram, TGroupButton, TH1, THistPainter, TLine, TLink, TMarker3DBox, TMarker, TNode, TPad, TPaletteAxis, TParallelCoord, TParallelCoordRange, TParallelCoordVar, TParticle, TPave, TPie, TPolyLine3D, TPolyLine, TPolyMarker3D, TPolyMarker, TPrimary, TScatter2D, TScatter, TSliderBox, TSpider, TSpline, TText, TTreePerfStats, TView3D, TView, TVirtualHistPainter, and TWbox.

Definition at line 415 of file TObject.cxx.

ExpandStructure()

void TMultiLayerPerceptron::ExpandStructure ( )

private

Expand the structure of the first layer.

Definition at line 1323 of file TMultiLayerPerceptron.cxx.

Export()

void TMultiLayerPerceptron::Export	(	Option_t *	filename = "NNfunction",
		Option_t *	language = "C++" ) const

Exports the NN as a function for any non-ROOT-dependant code Supported languages are: only C++ , FORTRAN and Python (yet) This feature is also useful if you want to plot the NN as a function (TF1 or TF2).

Definition at line 1737 of file TMultiLayerPerceptron.cxx.

Fatal()

void TObject::Fatal ( const char * location, const char * fmt, ... ) const

virtualinherited

Issue fatal error message.

Use "location" to specify the method where the fatal error occurred. Accepts standard printf formatting arguments.

Definition at line 1126 of file TObject.cxx.

FindObject() [1/2]

TObject * TObject::FindObject ( const char * name ) const

virtualinherited

Must be redefined in derived classes.

This function is typically used with TCollections, but can also be used to find an object by name inside this object.

Reimplemented in RooAbsCollection, RooLinkedList, TBtree, TCollection, TDirectory, TFolder, TGeometry, TGraph2D, TGraph, TH1, THashList, THashTable, THbookFile, TList, TListOfDataMembers, TListOfEnums, TListOfEnumsWithLock, TListOfFunctions, TListOfFunctionTemplates, TListOfTypes, TMap, TObjArray, TPad, TROOT, TViewPubDataMembers, and TViewPubFunctions.

Definition at line 425 of file TObject.cxx.

FindObject() [2/2]

TObject * TObject::FindObject ( const TObject * obj ) const

virtualinherited

Must be redefined in derived classes.

This function is typically used with TCollections, but can also be used to find an object inside this object.

Reimplemented in RooAbsCollection, RooLinkedList, TBtree, TCollection, TDirectory, TFolder, TGeometry, TGraph2D, TGraph, TH1, THashList, THashTable, THbookFile, TList, TListOfDataMembers, TListOfEnums, TListOfEnumsWithLock, TListOfFunctions, TListOfFunctionTemplates, TListOfTypes, TMap, TObjArray, TPad, TROOT, TViewPubDataMembers, and TViewPubFunctions.

Definition at line 435 of file TObject.cxx.

GetBFGSH()

bool TMultiLayerPerceptron::GetBFGSH ( TMatrixD & bfgsh, TMatrixD & gamma, TMatrixD & delta )

protected

Computes the hessian matrix using the BFGS update algorithm.

from gamma (g_{(t+1)}-g_{(t)}) and delta (w_{(t+1)}-w_{(t)}). It returns true if such a direction could not be found (if gamma and delta are orthogonal).

Definition at line 2404 of file TMultiLayerPerceptron.cxx.

GetCrossEntropy()

Double_t TMultiLayerPerceptron::GetCrossEntropy ( ) const

protected

Cross entropy error for a softmax output neuron, for a given event.

Definition at line 1141 of file TMultiLayerPerceptron.cxx.

GetCrossEntropyBinary()

Double_t TMultiLayerPerceptron::GetCrossEntropyBinary ( ) const

protected

Cross entropy error for sigmoid output neurons, for a given event.

Definition at line 1110 of file TMultiLayerPerceptron.cxx.

GetDelta()

Double_t TMultiLayerPerceptron::GetDelta ( ) const

inline

Definition at line 78 of file TMultiLayerPerceptron.h.

GetDrawOption()

Option_t * TObject::GetDrawOption ( ) const

virtualinherited

Get option used by the graphics system to draw this object.

Note that before calling object.GetDrawOption(), you must have called object.Draw(..) before in the current pad.

Reimplemented in TBrowser, TFitEditor, TGedFrame, TGFileBrowser, TRootBrowser, and TRootBrowserLite.

Definition at line 445 of file TObject.cxx.

GetDtorOnly()

Longptr_t TObject::GetDtorOnly ( )

staticinherited

Return destructor only flag.

Definition at line 1196 of file TObject.cxx.

GetEntry()

void TMultiLayerPerceptron::GetEntry ( Int_t entry ) const

protected

Load an entry into the network.

Definition at line 758 of file TMultiLayerPerceptron.cxx.

GetEpsilon()

Double_t TMultiLayerPerceptron::GetEpsilon ( ) const

inline

Definition at line 77 of file TMultiLayerPerceptron.h.

GetError() [1/2]

Double_t TMultiLayerPerceptron::GetError

(

Int_t

event

)

const

Error on the output for a given event.

Definition at line 1045 of file TMultiLayerPerceptron.cxx.

GetError() [2/2]

Double_t TMultiLayerPerceptron::GetError

(

TMultiLayerPerceptron::EDataSet

set

)

const

Error on the whole dataset.

Definition at line 1074 of file TMultiLayerPerceptron.cxx.

GetEta()

Double_t TMultiLayerPerceptron::GetEta ( ) const

inline

Definition at line 76 of file TMultiLayerPerceptron.h.

GetEtaDecay()

Double_t TMultiLayerPerceptron::GetEtaDecay ( ) const

inline

Definition at line 79 of file TMultiLayerPerceptron.h.

GetIconName()

const char * TObject::GetIconName ( ) const

virtualinherited

Returns mime type name of object.

Used by the TBrowser (via TGMimeTypes class). Override for class of which you would like to have different icons for objects of the same class.

Reimplemented in ROOT::Experimental::XRooFit::xRooNode, TASImage, TBranch, TBranchElement, TGeoVolume, TGMainFrame, TKey, TMethodBrowsable, TSystemFile, and TVirtualBranchBrowsable.

Definition at line 472 of file TObject.cxx.

GetLearningMethod()

TMultiLayerPerceptron::ELearningMethod TMultiLayerPerceptron::GetLearningMethod ( ) const

inline

Definition at line 80 of file TMultiLayerPerceptron.h.

GetName()

const char * TObject::GetName ( ) const

virtualinherited

Returns name of object.

This default method returns the class name. Classes that give objects a name should override this method.

Reimplemented in RooAbsCollection, RooCatType, RooLinkedList, TArchiveMember, TCollection, TEnvRec, TEveGeoNode, TGaxis, TGeoDecayChannel, TGeoShape, TGeoVGShape, TGLEmbeddedViewer, TGLPShapeObj, TGLSAViewer, TGMenuEntry, TGMenuTitle, TGPicture, TGWindow, TIconBoxThumb, TMapFile, TMVA::DataSetInfo, TMVA::FitterBase, TMVA::MethodBase, TMVA::OptionBase, TMVA::PDF, TMVA::Reader, TMVA::VariableTransformBase, TNamed, TObjString, TPad, TPair, TParameter< AParamType >, TParameter< Long64_t >, TParticle, TPave, TPolyMarker3D, TPrimary, TQCommand, TQConnection, TQSlot, TRealData, TSQLClassColumnInfo, TSQLClassInfo, TSQLColumnData, TStatistic, TStructNode, TTreePerfStats, TTVRecord, TTVSession, TVirtualGeoTrack, TVirtualPad, and TXMLAttr.

Definition at line 462 of file TObject.cxx.

GetObjectInfo()

char * TObject::GetObjectInfo ( Int_t px, Int_t py ) const

virtualinherited

Returns string containing info about the object at position (px,py).

This method is typically overridden by classes of which the objects can report peculiarities for different positions. Returned string will be re-used (lock in MT environment).

Reimplemented in TASImage, TAxis3D, TColorWheel, TF1, TF2, TFileDrawMap, TGeoNode, TGeoTrack, TGeoVolume, TGL5DDataSet, TGLHistPainter, TGLParametricEquation, TGLTH3Composition, TGraph, TH1, THistPainter, TNode, TPaletteAxis, TParallelCoordVar, and TVirtualHistPainter.

Definition at line 491 of file TObject.cxx.

GetObjectStat()

Bool_t TObject::GetObjectStat ( )

staticinherited

Get status of object stat flag.

Definition at line 1181 of file TObject.cxx.

GetOption()

virtual Option_t * TObject::GetOption ( ) const

inlinevirtualinherited

Reimplemented in TArrow, TAxis3D, TFile, TGaxis, TGeoVolume, TH1, THelix, TLegendEntry, TMapFile, TNode, TPave, TPoints3DABC, TPolyLine3D, TPolyLine, TPolyMarker3D, TPolyMarker, TPSocket, TSelector, TSocket, and TUDPSocket.

Definition at line 147 of file TObject.h.

GetReset()

Int_t TMultiLayerPerceptron::GetReset ( ) const

inline

Definition at line 82 of file TMultiLayerPerceptron.h.

GetStructure()

TString TMultiLayerPerceptron::GetStructure ( ) const

inline

Definition at line 83 of file TMultiLayerPerceptron.h.

GetSumSquareError()

Double_t TMultiLayerPerceptron::GetSumSquareError ( ) const

protected

Error on the output for a given event.

Definition at line 1097 of file TMultiLayerPerceptron.cxx.

GetTau()

Double_t TMultiLayerPerceptron::GetTau ( ) const

inline

Definition at line 81 of file TMultiLayerPerceptron.h.

GetTitle()

const char * TObject::GetTitle ( ) const

virtualinherited

Returns title of object.

This default method returns the class title (i.e. description). Classes that give objects a title should override this method.

Reimplemented in Axis2, TASImage, TAxis, TBaseClass, TClassMenuItem, TEveGeoNode, TEvePointSet, TGaxis, TGGroupFrame, TGLabel, TGLVEntry, TGTextButton, TGTextEntry, TGTextLBEntry, TKey, TMapFile, TNamed, TPad, TPair, TParallelCoordSelect, TParticle, TPaveLabel, TPrimary, TQCommand, TRootIconList, and TVirtualPad.

Definition at line 507 of file TObject.cxx.

GetType()

TNeuron::ENeuronType TMultiLayerPerceptron::GetType ( ) const

inline

Definition at line 84 of file TMultiLayerPerceptron.h.

GetUniqueID()

UInt_t TObject::GetUniqueID ( ) const

virtualinherited

Return the unique object id.

Definition at line 480 of file TObject.cxx.

HandleTimer()

Bool_t TObject::HandleTimer ( TTimer * timer )

virtualinherited

Execute action in response of a timer timing out.

This method must be overridden if an object has to react to timers.

Reimplemented in TGCommandPlugin, TGDNDManager, TGFileContainer, TGHtml, TGLEventHandler, TGPopupMenu, TGraphTime, TGScrollBar, TGShutter, TGTextEdit, TGTextEditor, TGTextEntry, TGTextView, TGToolTip, TGuiBldDragManager, TGWindow, and TTreeViewer.

Definition at line 516 of file TObject.cxx.

Hash()

ULong_t TObject::Hash ( ) const

virtualinherited

Return hash value for this object.

Note: If this routine is overloaded in a derived class, this derived class should also add

ROOT::CallRecursiveRemoveIfNeeded(*this)

Otherwise, when RecursiveRemove is called (by ~TObject or example) for this type of object, the transversal of THashList and THashTable containers will will have to be done without call Hash (and hence be linear rather than logarithmic complexity). You will also see warnings like

Error in <ROOT::Internal::TCheckHashRecursiveRemoveConsistency::CheckRecursiveRemove>: The class SomeName overrides
TObject::Hash but does not call TROOT::RecursiveRemove in its destructor.

Reimplemented in RooLinkedList, TASImagePlugin, TASPluginGS, TCollection, TEnvRec, TGObject, TGPicture, TIconBoxThumb, TImagePlugin, TNamed, TObjString, TPad, TPair, TParameter< AParamType >, TParameter< Long64_t >, TPave, and TStatistic.

Definition at line 539 of file TObject.cxx.

HasInconsistentHash()

Bool_t TObject::HasInconsistentHash ( ) const

inlineinherited

Return true is the type of this object is known to have an inconsistent setup for Hash and RecursiveRemove (i.e.

missing call to RecursiveRemove in destructor).

Note: Since the consistency is only tested for during inserts, this routine will return true for object that have never been inserted whether or not they have a consistent setup. This has no negative side-effect as searching for the object with the right or wrong Hash will always yield a not-found answer (Since anyway no hash can be guaranteed unique, there is always a check)

Definition at line 366 of file TObject.h.

Info()

void TObject::Info ( const char * location, const char * fmt, ... ) const

virtualinherited

Issue info message.

Use "location" to specify the method where the warning occurred. Accepts standard printf formatting arguments.

Definition at line 1072 of file TObject.cxx.

InheritsFrom() [1/2]

Bool_t TObject::InheritsFrom ( const char * classname ) const

virtualinherited

Returns kTRUE if object inherits from class "classname".

Reimplemented in TClass.

Definition at line 549 of file TObject.cxx.

InheritsFrom() [2/2]

Bool_t TObject::InheritsFrom ( const TClass * cl ) const

virtualinherited

Returns kTRUE if object inherits from TClass cl.

Reimplemented in TClass.

Definition at line 557 of file TObject.cxx.

Inspect()

void TObject::Inspect ( ) const

virtualinherited

Dump contents of this object in a graphics canvas.

Same action as Dump but in a graphical form. In addition pointers to other objects can be followed.

The following picture is the Inspect of a histogram object:

Reimplemented in ROOT::Experimental::XRooFit::xRooNode, TGFrame, TInspectorObject, and TSystemFile.

Definition at line 570 of file TObject.cxx.

InvertBit()

void TObject::InvertBit ( UInt_t f )

inlineinherited

Definition at line 206 of file TObject.h.

IsA()

TClass * TMultiLayerPerceptron::IsA ( ) const

inlineoverridevirtual

Returns

TClass describing current object

Reimplemented from TObject.

Definition at line 151 of file TMultiLayerPerceptron.h.

IsDestructed()

Bool_t TObject::IsDestructed ( ) const

inlineinherited

IsDestructed.

Note

This function must be non-virtual as it can be used on destructed (but not yet modified) memory. This is used for example in TClonesArray to record the element that have been destructed but not deleted and thus are ready for re-use (by operator new with placement).

Returns

true if this object's destructor has been run.

Definition at line 186 of file TObject.h.

IsEqual()

Bool_t TObject::IsEqual ( const TObject * obj ) const

virtualinherited

Default equal comparison (objects are equal if they have the same address in memory).

More complicated classes might want to override this function.

Reimplemented in TGObject, TObjString, TPair, and TQCommand.

Definition at line 589 of file TObject.cxx.

IsFolder()

Bool_t TObject::IsFolder ( ) const

virtualinherited

Returns kTRUE in case object contains browsable objects (like containers or lists of other objects).

Reimplemented in ROOT::Experimental::XRooFit::xRooNode, ROOT::Internal::THnBaseBrowsable, TApplicationRemote, TAxis3D, TBaseClass, TBranch, TBranchClones, TBranchElement, TBranchObject, TBranchSTL, TBrowserObject, TCanvas, TClass, TCollection, TDatabasePDG, TDirectory, TFolder, TGeoManager, TGeometry, TGeoNode, TGeoNodeMatrix, TGeoOverlap, TGeoTrack, TGeoVolume, THbookFile, THbookKey, THnBase, TKey, TMapFile, TMultiDimFit, TNode, TPad, TPair, TParticleClassPDG, TPrincipal, TRemoteObject, TROOT, TRootIconList, TSPlot, TSystemDirectory, TTask, TTree, and TVirtualBranchBrowsable.

Definition at line 579 of file TObject.cxx.

IsOnHeap()

Bool_t TObject::IsOnHeap ( ) const

inlineinherited

Definition at line 160 of file TObject.h.

IsSortable()

virtual Bool_t TObject::IsSortable ( ) const

inlinevirtualinherited

Reimplemented in RooAbsArg, RooDouble, TCollection, TFileInfo, TGeoBranchArray, TGeoOverlap, TGFSFrameElement, TGLBFrameElement, TNamed, TObjString, TParameter< AParamType >, TParameter< Long64_t >, TPave, TStructNode, TStructNodeProperty, TUri, and TUrl.

Definition at line 158 of file TObject.h.

IsZombie()

Bool_t TObject::IsZombie ( ) const

inlineinherited

Definition at line 161 of file TObject.h.

LineSearch()

bool TMultiLayerPerceptron::LineSearch ( Double_t * direction, Double_t * buffer )

protected

Search along the line defined by direction.

buffer is not used but is updated with the new dw so that it can be used by a later stochastic step. It returns true if the line search fails.

Definition at line 2273 of file TMultiLayerPerceptron.cxx.

LoadWeights()

Bool_t TMultiLayerPerceptron::LoadWeights

(

Option_t *

filename = ""

)

Loads the weights from a text file conforming to the format defined by DumpWeights.

Definition at line 1656 of file TMultiLayerPerceptron.cxx.

ls()

void TObject::ls ( Option_t * option = "" ) const

virtualinherited

The ls function lists the contents of a class on stdout.

Ls output is typically much less verbose then Dump().

Reimplemented in ROOT::Detail::TSchemaRuleSet, ROOT::Experimental::XRooFit::xRooBrowser, ROOT::TSchemaRule, TAnnotation, TApplication, TBox, TCanvas, TChain, TChainElement, TClass, TClassTree, TCollection, TColor, TDirectory, TDirectoryFile, TEllipse, TFile, TFolder, TFree, TFriendElement, TFunction, TGeometry, TGeoNode, TGFrameElement, TGLayoutHints, THbookFile, THStack, TImage, TKey, TLine, TMapFile, TMarker, TNamed, TNode, TPad, TParameter< AParamType >, TParameter< Long64_t >, TPave, TPolyLine3D, TPolyLine, TPolyMarker3D, TPolyMarker, TQCommand, TQConnection, TQConnectionList, TQSlot, TQUndoManager, TROOT, TStatistic, TStreamerBase, TStreamerElement, TStreamerInfo, TStreamerSTL, TTask, TText, TVirtualPad, and TVirtualStreamerInfo.

Definition at line 598 of file TObject.cxx.

MakeZombie()

void TObject::MakeZombie ( )

inlineprotectedinherited

Definition at line 55 of file TObject.h.

MayNotUse()

void TObject::MayNotUse ( const char * method ) const

inherited

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).

Definition at line 1160 of file TObject.cxx.

MLP_Batch()

void TMultiLayerPerceptron::MLP_Batch ( Double_t * buffer )

protected

One step for the batch (stochastic) method.

DEDw should have been updated before calling this.

Definition at line 2202 of file TMultiLayerPerceptron.cxx.

MLP_Line()

void TMultiLayerPerceptron::MLP_Line ( Double_t * origin, Double_t * dir, Double_t dist )

private

Sets the weights to a point along a line Weights are set to [origin + (dist * dir)].

Definition at line 2230 of file TMultiLayerPerceptron.cxx.

MLP_Stochastic()

void TMultiLayerPerceptron::MLP_Stochastic ( Double_t * buffer )

protected

One step for the stochastic method buffer should contain the previous dw vector and will be updated.

Definition at line 2157 of file TMultiLayerPerceptron.cxx.

Notify()

Bool_t TObject::Notify ( )

virtualinherited

This method must be overridden to handle object notification (the base implementation is no-op).

Different objects in ROOT use the Notify method for different purposes, in coordination with other objects that call this method at the appropriate time.

For example, TLeaf uses it to load class information; TBranchRef to load contents of referenced branches TBranchRef; most notably, based on Notify, TChain implements a callback mechanism to inform interested parties when it switches to a new sub-tree.

Reimplemented in h1analysis, h1analysisTreeReader, TARInterruptHandler, TASInputHandler, TASInterruptHandler, TASLogHandler, TASSigPipeHandler, TBlinkTimer, TBranchElement, TBranchRef, TBreakLineCom, TBrowserTimer, TCollection, TDelCharCom, TDelTextCom, TFileHandler, TGContainerKeyboardTimer, TGContainerScrollTimer, TGInputHandler, TGLRedrawTimer, TGTextEditHist, TGuiBldDragManagerRepeatTimer, TIdleTimer, TInsCharCom, TInsTextCom, TInterruptHandler, TLeafObject, TMessageHandler, TNotifyLink< Type >, TNotifyLink< RNoCleanupNotifierHelper >, TNotifyLink< ROOT::Detail::TBranchProxy >, TNotifyLink< TTreeReader >, TPopupDelayTimer, TProcessEventTimer, TRefTable, TRepeatTimer, TSBRepeatTimer, TSelector, TSelectorDraw, TSelectorEntries, TSignalHandler, TSingleShotCleaner, TSocketHandler, TStdExceptionHandler, TSysEvtHandler, TTermInputHandler, TThreadTimer, TTimeOutTimer, TTimer, TTipDelayTimer, TTree, TTreeFormula, TTreeFormulaManager, TTreeReader, TViewTimer, and TViewUpdateTimer.

Definition at line 618 of file TObject.cxx.

Obsolete()

void TObject::Obsolete ( const char * method, const char * asOfVers, const char * removedFromVers ) const

inherited

Use this method to declare a method obsolete.

Specify as of which version the method is obsolete and as from which version it will be removed.

Definition at line 1169 of file TObject.cxx.

operator delete() [1/3]

void TObject::operator delete ( void * ptr, size_t size )

inherited

Operator delete for sized deallocation.

Definition at line 1234 of file TObject.cxx.

operator delete() [2/3]

void TObject::operator delete ( void * ptr )

inherited

Operator delete.

Definition at line 1212 of file TObject.cxx.

operator delete() [3/3]

void TObject::operator delete ( void * ptr, void * vp )

inherited

Only called by placement new when throwing an exception.

Definition at line 1266 of file TObject.cxx.

operator delete[]() [1/3]

void TObject::operator delete[] ( void * ptr, size_t size )

inherited

Operator delete [] for sized deallocation.

Definition at line 1245 of file TObject.cxx.

operator delete[]() [2/3]

void TObject::operator delete[] ( void * ptr )

inherited

Operator delete [].

Definition at line 1223 of file TObject.cxx.

operator delete[]() [3/3]

void TObject::operator delete[] ( void * ptr, void * vp )

inherited

Only called by placement new[] when throwing an exception.

Definition at line 1274 of file TObject.cxx.

operator new() [1/2]

void * TObject::operator new ( size_t sz )

inlineinherited

Definition at line 189 of file TObject.h.

operator new() [2/2]

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

inlineinherited

Definition at line 191 of file TObject.h.

operator new[]() [1/2]

void * TObject::operator new[] ( size_t sz )

inlineinherited

Definition at line 190 of file TObject.h.

operator new[]() [2/2]

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

inlineinherited

Definition at line 192 of file TObject.h.

operator=()

TMultiLayerPerceptron & TMultiLayerPerceptron::operator= ( const TMultiLayerPerceptron & )

private

Paint()

void TObject::Paint ( Option_t * option = "" )

virtualinherited

This method must be overridden if a class wants to paint itself.

The difference between Paint() and Draw() is that when a object draws itself it is added to the display list of the pad in which it is drawn (and automatically redrawn whenever the pad is redrawn). While paint just draws the object without adding it to the pad display list.

Reimplemented in ROOT::Experimental::RTreeMapPainter, ROOT::RGeoPainter, TAnnotation, TArrow, TASImage, TASPaletteEditor::LimitLine, TASPaletteEditor::PaintPalette, TAxis3D, TBits, TBox, TButton, TCanvas, TClassTree, TCollection, TColorWheel, TCrown, TDiamond, TDirectory, TEfficiency, TEllipse, TEveArrow, TEveCaloViz, TEveDigitSet, TEveGeoShape, TEveGeoTopNode, TEvePlot3D, TEvePointSet, TEveProjectionAxes, TEveScene, TEveShape, TEveStraightLineSet, TEveText, TEveTriangleSet, TExec, TF1, TF2, TF3, TFile, TFileDrawMap, TFrame, TGaxis, TGenerator, TGeoBoolNode, TGeoIntersection, TGeoNode, TGeoOverlap, TGeoPainter, TGeoPhysicalNode, TGeoShape, TGeoSubtraction, TGeoTrack, TGeoUnion, TGeoVGShape, TGeoVolume, TGL5DDataSet, TGLHistPainter, TGLParametricEquation, TGLTH3Composition, TGraph2D, TGraph2DPainter, TGraph, TGraphEdge, TGraphNode, TGraphPolargram, TGraphTime, TH1, THistPainter, THStack, TLatex, TLegend, TLine, TMacro, TMarker3DBox, TMarker, TMathText, TMultiGraph, TNode, TNodeDiv, TPad, TPaletteAxis, TParallelCoord, TParallelCoordRange, TParallelCoordVar, TParticle, TPave, TPaveLabel, TPaveStats, TPavesText, TPaveText, TPie, TPolyLine3D, TPolyLine, TPolyMarker3D, TPolyMarker, TPrimary, TRatioPlot, TScatter2D, TScatter, TShape, TSpectrum2Painter, TSpider, TSpline, TSQLFile, TStyle, TText, TTreePerfStats, TVirtualGeoPainter, TVirtualGeoTrack, TVirtualHistPainter, TVirtualPad, TWbox, and TXMLFile.

Definition at line 631 of file TObject.cxx.

Pop()

void TObject::Pop ( )

virtualinherited

Pop on object drawn in a pad to the top of the display list.

I.e. it will be drawn last and on top of all other primitives.

Reimplemented in TFrame, TPad, and TVirtualPad.

Definition at line 640 of file TObject.cxx.

Print()

void TObject::Print ( Option_t * option = "" ) const

virtualinherited

This method must be overridden when a class wants to print itself.

Reimplemented in Roo1DTable, RooAbsArg, RooAbsBinning, RooAbsCollection, RooAbsData, RooAbsDataStore, RooAbsGenContext, RooCatType, RooCmdArg, RooCurve, RooEllipse, RooFitResult, RooGenFitStudy, RooHist, RooLinkedList, RooMsgService, RooNumGenConfig, RooNumIntConfig, RooPlot, RooSharedProperties, RooStats::ModelConfig, ROOT::Experimental::REveTrans, ROOT::Experimental::XRooFit::xRooNLLVar::xRooHypoPoint, ROOT::Experimental::XRooFit::xRooNLLVar::xRooHypoSpace, ROOT::Experimental::XRooFit::xRooNode, ROOT::v5::TFormula, RooWorkspace, TAnnotation, TApplicationRemote, TAttParticle, TBenchmark, TBits, TBox, TBranch, TBranchClones, TBranchElement, TBranchObject, TBranchRef, TBranchSTL, TChain, TClassTable, TCling, TCollection, TColor, TDatabasePDG, TDecompBase, TDecompBK, TDecompChol, TDecompLU, TDecompQRH, TDecompSparse, TDecompSVD, TDirectory, TEllipse, TEnv, TEventList, TEveTrans, TF1, TFile, TFileCacheRead, TFileCacheWrite, TFileCollection, TFileInfo, TFileInfoMeta, TFitResult, TFoamCell, TFoamVect, TFormula, TFunction, TGCompositeFrame, TGDMLMatrix, TGeoBatemanSol, TGeoBorderSurface, TGeoBranchArray, TGeoDecayChannel, TGeoElement, TGeoElementRN, TGeoElementTable, TGeoIsotope, TGeoMatrix, TGeoOpticalSurface, TGeoOverlap, TGeoPhysicalNode, TGeoRegion, TGeoSkinSurface, TGeoTessellated, TGeoTrack, TGeoVolume, TGeoVoxelFinder, TGFont, TGFontPool, TGFrame, TGFrameElement, TGGC, TGGCPool, TGLayoutHints, TGMimeTypes, TGPicture, TGPicturePool, TGraph2D, TGraph2DAsymmErrors, TGraph2DErrors, TGraph, TGraphAsymmErrors, TGraphBentErrors, TGraphErrors, TGraphMultiErrors, TGTextEdit, TGWindow, TH1, THashTable, THbookTree, THelix, THnBase, THStack, TInetAddress, TKey, TLegend, TLegendEntry, TLine, TLorentzVector, TMacro, TMapFile, TMarker, TMatrixTBase< Element >, TMatrixTBase< Double_t >, TMatrixTBase< Float_t >, TMemFile, TMessageHandler, TMultiDimFit, TMultiGraph, TMVA::Event, TMVA::Option< T >, TMVA::Option< T * >, TMVA::OptionBase, TMVA::PDEFoamCell, TMVA::PDEFoamVect, TMVA::TNeuron, TNamed, TObjectTable, TObjString, TPad, TParallelCoordRange, TParallelCoordVar, TParameter< AParamType >, TParameter< Long64_t >, TParticle, TParticleClassPDG, TParticlePDG, TPave, TPaveText, TPluginHandler, TPluginManager, TPolyLine3D, TPolyLine, TPolyMarker3D, TPolyMarker, TPrimary, TPrincipal, TQpDataDens, TQpDataSparse, TQpVar, TQSlot, TQuaternion, TRolke, TRootBrowserHistoryCursor, TScatter2D, TScatter, TSpectrum2, TSpectrum3, TSpectrum, TSQLColumnInfo, TSQLFile, TSQLStructure, TSQLTableInfo, TStatistic, TStopwatch, TStreamerInfoActions::TActionSequence, TText, TTree, TTreeCache, TTreeCacheUnzip, TTreeIndex, TTreePerfStats, TUri, TUrl, TVector2, TVector3, TVectorT< Element >, TVectorT< Double_t >, TVectorT< Float_t >, TVirtualPad, TXMLFile, TXTRU, TZIPFile, and TZIPMember.

Definition at line 661 of file TObject.cxx.

Randomize()

void TMultiLayerPerceptron::Randomize

(

)

const

Randomize the weights.

Definition at line 1238 of file TMultiLayerPerceptron.cxx.

Read()

Int_t TObject::Read ( const char * name )

virtualinherited

Read contents of object with specified name from the current directory.

First the key with the given name is searched in the current directory, next the key buffer is deserialized into the object. The object must have been created before via the default constructor. See TObject::Write().

Reimplemented in TBuffer, TKey, TKeySQL, and TKeyXML.

Definition at line 673 of file TObject.cxx.

RecursiveRemove()

void TObject::RecursiveRemove ( TObject * obj )

virtualinherited

Recursively remove this object from a list.

Typically implemented by classes that can contain multiple references to a same object.

Reimplemented in RooAbsCollection, RooAbsData, RooLinkedList, RooMCStudy, ROOT::Internal::TCheckHashRecursiveRemoveConsistency, ROOT::RBrowserDataCleanup, RooWorkspace, TBrowser, TChain, TCling, TCollection, TDialogCanvas, TDirectory, TEfficiency, TFileMerger, TFitEditor, TFolder, TFriendElement, TGedEditor, TGeometry, TGFileBrowser, TGraph2D, TGraph, TH1, TH1Editor, TH2Editor, THashList, THistPainter, THStack, TInspectCanvas, TLegend, TList, TListOfDataMembers, TListOfEnums, TListOfEnumsWithLock, TListOfFunctions, TListOfFunctionTemplates, TMultiGraph, TNode, TObjArray, TObjectRefSpy, TObjectSpy, TPad, TProcessID, TROOT, TRootBrowser, TRootBrowserHistory, TRootBrowserLite, TRootContextMenu, TTree, TTreePlayer, TViewPubDataMembers, TViewPubFunctions, and TVirtualPad.

Definition at line 684 of file TObject.cxx.

ResetBit()

void TObject::ResetBit ( UInt_t f )

inlineinherited

Definition at line 203 of file TObject.h.

Result()

Double_t TMultiLayerPerceptron::Result	(	Int_t	event,
		Int_t	index = 0 ) const

Computes the output for a given event.

Look at the output neuron designed by index.

Definition at line 1032 of file TMultiLayerPerceptron.cxx.

SaveAs()

void TObject::SaveAs ( const char * filename = "", Option_t * option = "" ) const

virtualinherited

Save this object in the file specified by filename.

• if "filename" contains ".root" the object is saved in filename as root binary file.
• if "filename" contains ".xml" the object is saved in filename as a xml ascii file.
• if "filename" contains ".cc" the object is saved in filename as C code independent from ROOT. The code is generated via SavePrimitive(). Specific code should be implemented in each object to handle this option. Like in TF1::SavePrimitive().

• otherwise the object is written to filename as a CINT/C++ script. The C++ code to rebuild this object is generated via SavePrimitive(). The "option" parameter is passed to SavePrimitive. By default it is an empty string. It can be used to specify the Draw option in the code generated by SavePrimitive.

  The function is available via the object context menu.

Reimplemented in ROOT::Experimental::XRooFit::xRooNode, TClassTree, TFolder, TGeoVolume, TGObject, TGraph, TH1, TPad, TPaveClass, TSpline3, TSpline5, TSpline, TTreePerfStats, and TVirtualPad.

Definition at line 708 of file TObject.cxx.

SavePrimitive()

void TObject::SavePrimitive ( std::ostream & out, Option_t * option = "" )

virtualinherited

Save a primitive as a C++ statement(s) on output stream "out".

Reimplemented in TAnnotation, TArc, TArrow, TASImage, TAxis3D, TBox, TButton, TCanvas, TChain, TCrown, TCurlyArc, TCurlyLine, TCutG, TDiamond, TEfficiency, TEllipse, TExec, TF12, TF1, TF2, TF3, TFrame, TGaxis, TGButton, TGButtonGroup, TGCanvas, TGCheckButton, TGColorSelect, TGColumnLayout, TGComboBox, TGCompositeFrame, TGContainer, TGDockableFrame, TGDoubleHSlider, TGDoubleVSlider, TGedMarkerSelect, TGedPatternSelect, TGeoArb8, TGeoBBox, TGeoBoolNode, TGeoCombiTrans, TGeoCompositeShape, TGeoCone, TGeoConeSeg, TGeoCtub, TGeoDecayChannel, TGeoElementRN, TGeoEltu, TGeoGtra, TGeoHalfSpace, TGeoHMatrix, TGeoHype, TGeoIdentity, TGeoIntersection, TGeoMaterial, TGeoMedium, TGeoMixture, TGeoPara, TGeoParaboloid, TGeoPatternCylPhi, TGeoPatternCylR, TGeoPatternParaX, TGeoPatternParaY, TGeoPatternParaZ, TGeoPatternSphPhi, TGeoPatternSphR, TGeoPatternSphTheta, TGeoPatternTrapZ, TGeoPatternX, TGeoPatternY, TGeoPatternZ, TGeoPcon, TGeoPgon, TGeoRotation, TGeoScaledShape, TGeoShapeAssembly, TGeoSphere, TGeoSubtraction, TGeoTessellated, TGeoTorus, TGeoTranslation, TGeoTrap, TGeoTrd1, TGeoTrd2, TGeoTube, TGeoTubeSeg, TGeoUnion, TGeoVolume, TGeoXtru, TGFileContainer, TGFont, TGFrame, TGFSComboBox, TGGC, TGGroupFrame, TGHButtonGroup, TGHorizontal3DLine, TGHorizontalFrame, TGHorizontalLayout, TGHProgressBar, TGHScrollBar, TGHSlider, TGHSplitter, TGHtml, TGIcon, TGLabel, TGLayoutHints, TGLineStyleComboBox, TGLineWidthComboBox, TGListBox, TGListDetailsLayout, TGListLayout, TGListTree, TGListView, TGLVContainer, TGMainFrame, TGMatrixLayout, TGMdiFrame, TGMdiMainFrame, TGMdiMenuBar, TGMenuBar, TGMenuTitle, TGNumberEntry, TGNumberEntryField, TGPictureButton, TGPopupMenu, TGProgressBar, TGRadioButton, TGraph2D, TGraph2DAsymmErrors, TGraph2DErrors, TGraph, TGraphAsymmErrors, TGraphBentErrors, TGraphEdge, TGraphErrors, TGraphMultiErrors, TGraphNode, TGraphPolar, TGraphPolargram, TGraphStruct, TGroupButton, TGRowLayout, TGShapedFrame, TGShutter, TGShutterItem, TGSplitFrame, TGStatusBar, TGTab, TGTabLayout, TGTableLayout, TGTableLayoutHints, TGTextButton, TGTextEdit, TGTextEntry, TGTextLBEntry, TGTextView, TGTileLayout, TGToolBar, TGTransientFrame, TGTripleHSlider, TGTripleVSlider, TGVButtonGroup, TGVertical3DLine, TGVerticalFrame, TGVerticalLayout, TGVFileSplitter, TGVProgressBar, TGVScrollBar, TGVSlider, TGVSplitter, TGXYLayout, TGXYLayoutHints, TH1, TH2Poly, THelix, THStack, TLatex, TLegend, TLine, TMacro, TMarker3DBox, TMarker, TMathText, TMultiGraph, TPad, TPaletteAxis, TParallelCoord, TParallelCoordVar, TPave, TPaveClass, TPaveLabel, TPaveStats, TPavesText, TPaveText, TPie, TPieSlice, TPolyLine3D, TPolyLine, TPolyMarker3D, TPolyMarker, TProfile2D, TProfile3D, TProfile, TRootContainer, TRootEmbeddedCanvas, TScatter2D, TScatter, TSlider, TSliderBox, TSpline3, TSpline5, TStyle, TText, TTreePerfStats, and TWbox.

Definition at line 858 of file TObject.cxx.

SavePrimitiveConstructor()

void TObject::SavePrimitiveConstructor ( std::ostream & out, TClass * cl, const char * variable_name, const char * constructor_agrs = "", Bool_t empty_line = kTRUE )

staticprotectedinherited

Save object constructor in the output stream "out".

Can be used as first statement when implementing SavePrimitive() method for the object

Definition at line 777 of file TObject.cxx.

SavePrimitiveDraw()

void TObject::SavePrimitiveDraw ( std::ostream & out, const char * variable_name, Option_t * option = nullptr )

staticprotectedinherited

Save invocation of primitive Draw() method Skipped if option contains "nodraw" string.

Definition at line 845 of file TObject.cxx.

SavePrimitiveVector()

TString TObject::SavePrimitiveVector ( std::ostream & out, const char * prefix, Int_t len, Double_t * arr, Int_t flag = 0 )

staticprotectedinherited

Save array in the output stream "out" as vector.

Create unique variable name based on prefix value Returns name of vector which can be used in constructor or in other places of C++ code If flag === kTRUE, just add empty line If flag === 111, check if array is empty and return nullptr or <vectorname>.data()

Definition at line 796 of file TObject.cxx.

SetBit() [1/2]

void TObject::SetBit ( UInt_t f )

inlineinherited

Definition at line 202 of file TObject.h.

SetBit() [2/2]

void TObject::SetBit ( UInt_t f, Bool_t set )

inherited

Set or unset the user status bits as specified in f.

Definition at line 888 of file TObject.cxx.

SetData()

void TMultiLayerPerceptron::SetData

(

TTree *

data

)

Set the data source.

Definition at line 589 of file TMultiLayerPerceptron.cxx.

SetDelta()

void TMultiLayerPerceptron::SetDelta

(

Double_t

delta

)

Sets Delta - used in stochastic minimisation (look at the constructor for the complete description of learning methods and parameters).

Definition at line 719 of file TMultiLayerPerceptron.cxx.

SetDrawOption()

void TObject::SetDrawOption ( Option_t * option = "" )

virtualinherited

Set drawing option for object.

This option only affects the drawing style and is stored in the option field of the TObjOptLink supporting a TPad's primitive list (TList). Note that it does not make sense to call object.SetDrawOption(option) before having called object.Draw().

Reimplemented in RooPlot, TAxis, TBrowser, TGedFrame, TGFrame, TPad, TPaveStats, TRootBrowserLite, TSystemDirectory, and TSystemFile.

Definition at line 871 of file TObject.cxx.

SetDtorOnly()

void TObject::SetDtorOnly ( void * obj )

staticinherited

Set destructor only flag.

Definition at line 1204 of file TObject.cxx.

SetEpsilon()

void TMultiLayerPerceptron::SetEpsilon

(

Double_t

eps

)

Sets Epsilon - used in stochastic minimisation (look at the constructor for the complete description of learning methods and parameters).

Definition at line 709 of file TMultiLayerPerceptron.cxx.

SetEta()

void TMultiLayerPerceptron::SetEta

(

Double_t

eta

)

Sets Eta - used in stochastic minimisation (look at the constructor for the complete description of learning methods and parameters).

Definition at line 699 of file TMultiLayerPerceptron.cxx.

SetEtaDecay()

void TMultiLayerPerceptron::SetEtaDecay

(

Double_t

ed

)

Sets EtaDecay - Eta *= EtaDecay at each epoch (look at the constructor for the complete description of learning methods and parameters).

Definition at line 729 of file TMultiLayerPerceptron.cxx.

SetEventWeight()

void TMultiLayerPerceptron::SetEventWeight

(

const char *

branch

)

Set the event weight.

Definition at line 605 of file TMultiLayerPerceptron.cxx.

SetGammaDelta()

void TMultiLayerPerceptron::SetGammaDelta ( TMatrixD & gamma, TMatrixD & delta, Double_t * buffer )

protected

Sets the gamma \((g_{(t+1)}-g_{(t)})\) and delta \((w_{(t+1)}-w_{(t)})\) vectors Gamma is computed here, so ComputeDEDw cannot have been called before, and delta is a direct translation of buffer into a TMatrixD.

Definition at line 2430 of file TMultiLayerPerceptron.cxx.

SetLearningMethod()

void TMultiLayerPerceptron::SetLearningMethod

(

TMultiLayerPerceptron::ELearningMethod

method

)

Sets the learning method.

Available methods are: kStochastic, kBatch, kSteepestDescent, kRibierePolak, kFletcherReeves and kBFGS. (look at the constructor for the complete description of learning methods and parameters)

Definition at line 689 of file TMultiLayerPerceptron.cxx.

SetObjectStat()

void TObject::SetObjectStat ( Bool_t stat )

staticinherited

Turn on/off tracking of objects in the TObjectTable.

Definition at line 1188 of file TObject.cxx.

SetReset()

void TMultiLayerPerceptron::SetReset

(

Int_t

reset

)

Sets number of epochs between two resets of the search direction to the steepest descent.

(look at the constructor for the complete description of learning methods and parameters)

Definition at line 750 of file TMultiLayerPerceptron.cxx.

SetTau()

void TMultiLayerPerceptron::SetTau

(

Double_t

tau

)

Sets Tau - used in line search (look at the constructor for the complete description of learning methods and parameters).

Definition at line 739 of file TMultiLayerPerceptron.cxx.

SetTestDataSet() [1/2]

void TMultiLayerPerceptron::SetTestDataSet

(

const char *

test

)

Sets the Test dataset.

Those events will not be used for the minimization but for control. Note that the tree must be already defined.

Definition at line 665 of file TMultiLayerPerceptron.cxx.

SetTestDataSet() [2/2]

void TMultiLayerPerceptron::SetTestDataSet

(

TEventList *

test

)

Sets the Test dataset.

Those events will not be used for the minimization but for control

Definition at line 632 of file TMultiLayerPerceptron.cxx.

SetTrainingDataSet() [1/2]

void TMultiLayerPerceptron::SetTrainingDataSet

(

const char *

train

)

Sets the Training dataset.

Those events will be used for the minimization. Note that the tree must be already defined.

Definition at line 644 of file TMultiLayerPerceptron.cxx.

SetTrainingDataSet() [2/2]

void TMultiLayerPerceptron::SetTrainingDataSet

(

TEventList *

train

)

Sets the Training dataset.

Those events will be used for the minimization

Definition at line 621 of file TMultiLayerPerceptron.cxx.

SetUniqueID()

void TObject::SetUniqueID ( UInt_t uid )

virtualinherited

Set the unique object id.

Definition at line 899 of file TObject.cxx.

Shuffle()

void TMultiLayerPerceptron::Shuffle ( Int_t * index, Int_t n ) const

private

Shuffle the Int_t index[n] in input.

Input:

• index: the array to shuffle
• n: the size of the array

Output:

• index: the shuffled indexes

This method is used for stochastic training

Definition at line 2138 of file TMultiLayerPerceptron.cxx.

SteepestDir()

void TMultiLayerPerceptron::SteepestDir ( Double_t * dir )

protected

Sets the search direction to steepest descent.

Definition at line 2252 of file TMultiLayerPerceptron.cxx.

Streamer()

void TMultiLayerPerceptron::Streamer ( TBuffer & R__b )

overridevirtual

Stream an object of class TObject.

Reimplemented from TObject.

StreamerNVirtual()

void TMultiLayerPerceptron::StreamerNVirtual ( TBuffer & ClassDef_StreamerNVirtual_b )

inline

Definition at line 151 of file TMultiLayerPerceptron.h.

SysError()

void TObject::SysError ( const char * location, const char * fmt, ... ) const

virtualinherited

Issue system error message.

Use "location" to specify the method where the system error occurred. Accepts standard printf formatting arguments.

Definition at line 1112 of file TObject.cxx.

TestBit()

Bool_t TObject::TestBit ( UInt_t f ) const

inlineinherited

Definition at line 204 of file TObject.h.

TestBits()

Int_t TObject::TestBits ( UInt_t f ) const

inlineinherited

Definition at line 205 of file TObject.h.

Train()

void TMultiLayerPerceptron::Train	(	Int_t	nEpoch,
		Option_t *	option = "text",
		Double_t	minE = 0 )

Train the network.

nEpoch is the number of iterations. option can contain:

• "text" (simple text output)
• "graph" (evoluting graphical training curves)
• "update=X" (step for the text/graph output update)
• "+" will skip the randomisation and start from the previous values.
• "current" (draw in the current canvas)
• "minErrorTrain" (stop when NN error on the training sample gets below minE
• "minErrorTest" (stop when NN error on the test sample gets below minE All combinations are available.

Definition at line 787 of file TMultiLayerPerceptron.cxx.

UseCurrentStyle()

void TObject::UseCurrentStyle ( )

virtualinherited

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

Reimplemented in TAxis3D, TCanvas, TFrame, TGraph, TH1, TPad, TPaveStats, TPaveText, and TTree.

Definition at line 909 of file TObject.cxx.

Warning()

void TObject::Warning ( const char * location, const char * fmt, ... ) const

virtualinherited

Issue warning message.

Use "location" to specify the method where the warning occurred. Accepts standard printf formatting arguments.

Definition at line 1084 of file TObject.cxx.

Write() [1/2]

Int_t TObject::Write ( const char * name = nullptr, Int_t option = 0, Int_t bufsize = 0 )

virtualinherited

Write this object to the current directory.

For more see the const version of this method.

Reimplemented in ROOT::TBufferMergerFile, TBuffer, TCollection, TDirectory, TDirectoryFile, TFile, TMap, TParallelMergingFile, TSQLFile, TTree, and TXMLFile.

Definition at line 989 of file TObject.cxx.

Write() [2/2]

Int_t TObject::Write ( const char * name = nullptr, Int_t option = 0, Int_t bufsize = 0 ) const

virtualinherited

Write this object to the current directory.

The data structure corresponding to this object is serialized. The corresponding buffer is written to the current directory with an associated key with name "name".

Writing an object to a file involves the following steps:

• Creation of a support TKey object in the current directory. The TKey object creates a TBuffer object.
• The TBuffer object is filled via the class::Streamer function.
• If the file is compressed (default) a second buffer is created to hold the compressed buffer.
• Reservation of the corresponding space in the file by looking in the TFree list of free blocks of the file.
• The buffer is written to the file.

Bufsize can be given to force a given buffer size to write this object. By default, the buffersize will be taken from the average buffer size of all objects written to the current file so far.

If a name is specified, it will be the name of the key. If name is not given, the name of the key will be the name as returned by GetName().

The option can be a combination of: kSingleKey, kOverwrite or kWriteDelete Using the kOverwrite option a previous key with the same name is overwritten. The previous key is deleted before writing the new object. Using the kWriteDelete option a previous key with the same name is deleted only after the new object has been written. This option is safer than kOverwrite but it is slower. NOTE: Neither kOverwrite nor kWriteDelete reduces the size of a TFile– the space is simply freed up to be overwritten; in the case of a TTree, it is more complicated. If one opens a TTree, appends some entries, then writes it out, the behaviour is effectively the same. If, however, one creates a new TTree and writes it out in this way, only the metadata is replaced, effectively making the old data invisible without deleting it. TTree::Delete() can be used to mark all disk space occupied by a TTree as free before overwriting its metadata this way. The kSingleKey option is only used by TCollection::Write() to write a container with a single key instead of each object in the container with its own key.

An object is read from the file into memory via TKey::Read() or via TObject::Read().

The function returns the total number of bytes written to the file. It returns 0 if the object cannot be written.

Reimplemented in TBuffer, TCollection, TDirectory, TDirectoryFile, TFile, TMap, TParallelMergingFile, TSQLFile, TTree, and TXMLFile.

Definition at line 964 of file TObject.cxx.

Friends And Related Symbol Documentation

TMLPAnalyzer

friend class TMLPAnalyzer

friend

Definition at line 27 of file TMultiLayerPerceptron.h.

Member Data Documentation

fBits

UInt_t TObject::fBits

privateinherited

bit field status word

Definition at line 47 of file TObject.h.

fCurrentTree

Int_t TMultiLayerPerceptron::fCurrentTree

private

! index of the current tree in a chain

Definition at line 124 of file TMultiLayerPerceptron.h.

fCurrentTreeWeight

Double_t TMultiLayerPerceptron::fCurrentTreeWeight

private

! weight of the current tree in a chain

Definition at line 125 of file TMultiLayerPerceptron.h.

fData

TTree* TMultiLayerPerceptron::fData

private

! pointer to the tree used as datasource

Definition at line 123 of file TMultiLayerPerceptron.h.

fDelta

Double_t TMultiLayerPerceptron::fDelta

private

! Delta - used in stochastic minimisation - Default=0.

Definition at line 143 of file TMultiLayerPerceptron.h.

fEpsilon

Double_t TMultiLayerPerceptron::fEpsilon

private

! Epsilon - used in stochastic minimisation - Default=0.

Definition at line 142 of file TMultiLayerPerceptron.h.

fEta

Double_t TMultiLayerPerceptron::fEta

private

! Eta - used in stochastic minimisation - Default=0.1

Definition at line 141 of file TMultiLayerPerceptron.h.

fEtaDecay

Double_t TMultiLayerPerceptron::fEtaDecay

private

! EtaDecay - Eta *= EtaDecay at each epoch - Default=1.

Definition at line 144 of file TMultiLayerPerceptron.h.

fEventWeight

TTreeFormula* TMultiLayerPerceptron::fEventWeight

private

! formula representing the event weight

Definition at line 139 of file TMultiLayerPerceptron.h.

fextD

TString TMultiLayerPerceptron::fextD

private

String containing the derivative name.

Definition at line 135 of file TMultiLayerPerceptron.h.

fextF

TString TMultiLayerPerceptron::fextF

private

String containing the function name.

Definition at line 134 of file TMultiLayerPerceptron.h.

fFirstLayer

TObjArray TMultiLayerPerceptron::fFirstLayer

private

Collection of the input neurons; subset of fNetwork.

Definition at line 127 of file TMultiLayerPerceptron.h.

fgDtorOnly

Longptr_t TObject::fgDtorOnly = 0

staticprivateinherited

object for which to call dtor only (i.e. no delete)

Definition at line 49 of file TObject.h.

fgObjectStat

Bool_t TObject::fgObjectStat = kTRUE

staticprivateinherited

if true keep track of objects in TObjectTable

Definition at line 50 of file TObject.h.

fLastAlpha

Double_t TMultiLayerPerceptron::fLastAlpha

private

! internal parameter used in line search

Definition at line 146 of file TMultiLayerPerceptron.h.

fLastLayer

TObjArray TMultiLayerPerceptron::fLastLayer

private

Collection of the output neurons; subset of fNetwork.

Definition at line 128 of file TMultiLayerPerceptron.h.

fLearningMethod

ELearningMethod TMultiLayerPerceptron::fLearningMethod

private

! The Learning Method

Definition at line 138 of file TMultiLayerPerceptron.h.

fManager

TTreeFormulaManager* TMultiLayerPerceptron::fManager

private

! TTreeFormulaManager for the weight and neurons

Definition at line 140 of file TMultiLayerPerceptron.h.

fNetwork

TObjArray TMultiLayerPerceptron::fNetwork

private

Collection of all the neurons in the network.

Definition at line 126 of file TMultiLayerPerceptron.h.

fOutType

TNeuron::ENeuronType TMultiLayerPerceptron::fOutType

private

Type of output neurons.

Definition at line 133 of file TMultiLayerPerceptron.h.

fReset

Int_t TMultiLayerPerceptron::fReset

private

! number of epochs between two resets of the search direction to the steepest descent - Default=50

Definition at line 147 of file TMultiLayerPerceptron.h.

fStructure

TString TMultiLayerPerceptron::fStructure

private

String containing the network structure.

Definition at line 130 of file TMultiLayerPerceptron.h.

fSynapses

TObjArray TMultiLayerPerceptron::fSynapses

private

Collection of all the synapses in the network.

Definition at line 129 of file TMultiLayerPerceptron.h.

fTau

Double_t TMultiLayerPerceptron::fTau

private

! Tau - used in line search - Default=3.

Definition at line 145 of file TMultiLayerPerceptron.h.

fTest

TEventList* TMultiLayerPerceptron::fTest

private

! EventList defining the events in the test dataset

Definition at line 137 of file TMultiLayerPerceptron.h.

fTestOwner

Bool_t TMultiLayerPerceptron::fTestOwner

private

! internal flag whether one has to delete fTest or not

Definition at line 149 of file TMultiLayerPerceptron.h.

fTraining

TEventList* TMultiLayerPerceptron::fTraining

private

! EventList defining the events in the training dataset

Definition at line 136 of file TMultiLayerPerceptron.h.

fTrainingOwner

Bool_t TMultiLayerPerceptron::fTrainingOwner

private

! internal flag whether one has to delete fTraining or not

Definition at line 148 of file TMultiLayerPerceptron.h.

fType

TNeuron::ENeuronType TMultiLayerPerceptron::fType

private

Type of hidden neurons.

Definition at line 132 of file TMultiLayerPerceptron.h.

fUniqueID

UInt_t TObject::fUniqueID

privateinherited

object unique identifier

Definition at line 46 of file TObject.h.

fWeight

TString TMultiLayerPerceptron::fWeight

private

String containing the event weight.

Definition at line 131 of file TMultiLayerPerceptron.h.

---

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

• math/mlp/inc/TMultiLayerPerceptron.h
• math/mlp/src/TMultiLayerPerceptron.cxx