This class describes an elementary neuron, which is the basic element for a Neural Network.

A network is built connecting neurons by synapses. There are different types of neurons: linear (a+bx), sigmoid (1/(1+exp(-x)), tanh or gaussian. An external function can also be used, together with its derivative. In a Multi Layer Perceptron, the input layer is made of inactive neurons (returning the normalized input) and output neurons are linear. Hidden neurons may be anything, the default being sigmoids.

This implementation contains several methods to compute the value, the derivative, the DeDw, ... Values are stored in local buffers. The SetNewEvent() method is there to inform buffered values are outdated.

Definition at line 25 of file TNeuron.h.

Public Types
enum	ENeuronType { kOff , kLinear , kSigmoid , kTanh , kGauss , kSoftmax , kExternal }

Public Types inherited from TObject
enum	{ kIsOnHeap = 0x01000000 , kNotDeleted = 0x02000000 , kZombie = 0x04000000 , kInconsistent = 0x08000000 , kBitMask = 0x00ffffff }

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

enum	EDeprecatedStatusBits { kObjInCanvas = BIT(3) }

enum	EStatusBits { kCanDelete = BIT(0) , kMustCleanup = BIT(3) , kIsReferenced = BIT(4) , kHasUUID = BIT(5) , kCannotPick = BIT(6) , kNoContextMenu = BIT(8) , kInvalidObject = BIT(13) }

Public Member Functions
	TNeuron (ENeuronType type=kSigmoid, const char name="", const char title="", const char extF="", const char extD="")
	Usual constructor.

virtual	~TNeuron ()

void	AddInLayer (TNeuron *)
	Tells a neuron which neurons form its layer (including itself).

void	ForceExternalValue (Double_t value)
	Uses the branch type to force an external value.

Double_t	GetBranch () const
	Returns the formula value.

Double_t	GetDeDw () const
	Computes the derivative of the error wrt the neuron weight.

Double_t	GetDEDw () const

Double_t	GetDerivative () const
	computes the derivative for the appropriate function at the working point

Double_t	GetError () const
	Computes the error for output neurons.

TNeuron *	GetInLayer (Int_t n) const

Double_t	GetInput () const
	Returns neuron input.

const Double_t *	GetNormalisation () const

TSynapse *	GetPost (Int_t n) const

TSynapse *	GetPre (Int_t n) const

Double_t	GetTarget () const
	Computes the normalized target pattern for output neurons.

ENeuronType	GetType () const
	Returns the neuron type.

Double_t	GetValue () const
	Computes the output using the appropriate function and all the weighted inputs, or uses the branch as input.

Double_t	GetWeight () const

void	SetDEDw (Double_t in)
	Sets the derivative of the total error wrt the neuron weight.

void	SetNewEvent () const
	Inform the neuron that inputs of the network have changed, so that the buffered values have to be recomputed.

void	SetNormalisation (Double_t mean, Double_t RMS)
	Sets the normalization variables.

void	SetWeight (Double_t w)
	Sets the neuron weight to w.

TTreeFormula *	UseBranch (TTree , const char )
	Sets a formula that can be used to make the neuron an input.

Public Member Functions inherited from TNamed
	TNamed ()

	TNamed (const char name, const char title)

	TNamed (const TNamed &named)
	TNamed copy ctor.

	TNamed (const TString &name, const TString &title)

virtual	~TNamed ()
	TNamed destructor.

virtual void	Clear (Option_t *option="")
	Set name and title to empty strings ("").

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 two TNamed objects.

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

virtual void	FillBuffer (char *&buffer)
	Encode TNamed into output buffer.

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

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

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

virtual Bool_t	IsSortable () const

virtual void	ls (Option_t *option="") const
	List TNamed name and title.

TNamed &	operator= (const TNamed &rhs)
	TNamed assignment operator.

virtual void	Print (Option_t *option="") const
	Print TNamed name and title.

virtual void	SetName (const char *name)
	Set the name of the TNamed.

virtual void	SetNameTitle (const char name, const char title)
	Set all the TNamed parameters (name and title).

virtual void	SetTitle (const char *title="")
	Set the title of the TNamed.

virtual Int_t	Sizeof () const
	Return size of the TNamed part of the TObject.

Public Member Functions inherited from TObject
	TObject ()
	TObject constructor.

	TObject (const TObject &object)
	TObject copy ctor.

virtual	~TObject ()
	TObject destructor.

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

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	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.

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

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 for instance with: `gROOT->SetSelectedPad(gPad)`.

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

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

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

virtual void	Execute (TMethod method, TObjArray params, Int_t *error=0)
	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).

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.

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

virtual const char *	GetIconName () const
	Returns mime type 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

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.

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)

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).

R__ALWAYS_INLINE Bool_t	IsOnHeap () const

R__ALWAYS_INLINE Bool_t	IsZombie () const

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.

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

void	operator delete (void *ptr)
	Operator delete.

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

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)

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

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 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)

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.

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

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

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

R__ALWAYS_INLINE Bool_t	TestBit (UInt_t f) const

Int_t	TestBits (UInt_t f) const

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=0, Int_t option=0, Int_t bufsize=0)
	Write this object to the current directory.

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

Protected Member Functions
void	AddPost (TSynapse *)
	Adds a synapse to the neuron as an output This method is used by the TSynapse while connecting two neurons.

void	AddPre (TSynapse *)
	Adds a synapse to the neuron as an input This method is used by the TSynapse while connecting two neurons.

Double_t	DSigmoid (Double_t x) const
	The Derivative of the Sigmoid.

Double_t	Sigmoid (Double_t x) const
	The Sigmoid.

Protected Member Functions inherited from TObject
virtual void	DoError (int level, const char location, const char fmt, va_list va) const
	Interface to ErrorHandler (protected).

void	MakeZombie ()

Private Member Functions
	TNeuron (const TNeuron &)

TNeuron &	operator= (const TNeuron &)

Private Attributes
Double_t	fDeDw
	! buffer containing the last derivative of the error

Double_t	fDEDw
	! buffer containing the sum over all examples of DeDw

Double_t	fDerivative
	! buffer containing the last neuron derivative

TFormula *	fExtD
	derivative (external mode)

TFormula *	fExtF
	function (external mode)

TTreeFormula *	fFormula
	! formula to be used for inputs and outputs

Int_t	fIndex
	! index in the formula

Double_t	fInput
	! buffer containing the last neuron input

TObjArray	flayer
	pointers to the current level in a network (neurons, not synapses)

Bool_t	fNewDeDw
	! do we need to compute fDeDw again ?

Bool_t	fNewDeriv
	! do we need to compute fDerivative again ?

Bool_t	fNewInput
	! do we need to compute fInput again ?

Bool_t	fNewValue
	! do we need to compute fValue again ?

Double_t	fNorm [2]
	normalisation to mean=0, RMS=1.

TObjArray	fpost
	pointers to the next level in a network

TObjArray	fpre
	pointers to the previous level in a network

ENeuronType	fType
	neuron type

Double_t	fValue
	! buffer containing the last neuron output

Double_t	fWeight
	weight used for computation

Friends
class	TSynapse

Additional Inherited Members
Static Public Member Functions inherited from TObject
static Long_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 inherited from TObject
enum	{ kOnlyPrepStep = BIT(3) }

Protected Attributes inherited from TNamed
TString	fName

TString	fTitle

#include <TMVA/TNeuron.h>

Inheritance diagram for TNeuron:

[legend]

Member Enumeration Documentation

◆ ENeuronType

enum TNeuron::ENeuronType

Enumerator
kOff
kLinear
kSigmoid
kTanh
kGauss
kSoftmax
kExternal

Definition at line 29 of file TNeuron.h.

Constructor & Destructor Documentation

◆ TNeuron() [1/2]

TNeuron::TNeuron	(	TNeuron::ENeuronType	type = `kSigmoid`,
		const char *	name = `""`,
		const char *	title = `""`,
		const char *	extF = `""`,
		const char *	extD = `""`
	)

Usual constructor.

Definition at line 47 of file TNeuron.cxx.

◆ ~TNeuron()

virtual TNeuron::~TNeuron ( )

inlinevirtual

Definition at line 34 of file TNeuron.h.

◆ TNeuron() [2/2]

TNeuron::TNeuron ( const TNeuron & )

private

Member Function Documentation

◆ AddInLayer()

void TNeuron::AddInLayer ( TNeuron * nearP )

Tells a neuron which neurons form its layer (including itself).

This is needed for self-normalizing functions, like Softmax.

Definition at line 853 of file TNeuron.cxx.

◆ AddPost()

void TNeuron::AddPost ( TSynapse * post )

protected

Adds a synapse to the neuron as an output This method is used by the TSynapse while connecting two neurons.

Definition at line 842 of file TNeuron.cxx.

◆ AddPre()

void TNeuron::AddPre ( TSynapse * pre )

protected

Adds a synapse to the neuron as an input This method is used by the TSynapse while connecting two neurons.

Definition at line 830 of file TNeuron.cxx.

◆ DSigmoid()

Double_t TNeuron::DSigmoid ( Double_t x ) const

protected

The Derivative of the Sigmoid.

Definition at line 814 of file TNeuron.cxx.

◆ ForceExternalValue()

void TNeuron::ForceExternalValue ( Double_t value )

Uses the branch type to force an external value.

Definition at line 1121 of file TNeuron.cxx.

◆ GetBranch()

Double_t TNeuron::GetBranch ( ) const

Returns the formula value.

Definition at line 910 of file TNeuron.cxx.

◆ GetDeDw()

Double_t TNeuron::GetDeDw ( ) const

Computes the derivative of the error wrt the neuron weight.

Definition at line 1080 of file TNeuron.cxx.

◆ GetDEDw()

Double_t TNeuron::GetDEDw ( ) const

inline

Definition at line 53 of file TNeuron.h.

◆ GetDerivative()

Double_t TNeuron::GetDerivative ( ) const

computes the derivative for the appropriate function at the working point

Definition at line 1007 of file TNeuron.cxx.

◆ GetError()

Double_t TNeuron::GetError ( ) const

Computes the error for output neurons.

Returns 0 for other neurons.

Definition at line 1059 of file TNeuron.cxx.

◆ GetInLayer()

TNeuron * TNeuron::GetInLayer ( Int_t n ) const

inline

Definition at line 37 of file TNeuron.h.

◆ GetInput()

Double_t TNeuron::GetInput ( ) const

Returns neuron input.

Definition at line 921 of file TNeuron.cxx.

◆ GetNormalisation()

const Double_t * TNeuron::GetNormalisation ( ) const

inline

Definition at line 50 of file TNeuron.h.

◆ GetPost()

TSynapse * TNeuron::GetPost ( Int_t n ) const

inline

Definition at line 36 of file TNeuron.h.

◆ GetPre()

TSynapse * TNeuron::GetPre ( Int_t n ) const

inline

Definition at line 35 of file TNeuron.h.

◆ GetTarget()

Double_t TNeuron::GetTarget ( ) const

Computes the normalized target pattern for output neurons.

Returns 0 for other neurons.

Definition at line 1070 of file TNeuron.cxx.

◆ GetType()

TNeuron::ENeuronType TNeuron::GetType ( ) const

Returns the neuron type.

Definition at line 863 of file TNeuron.cxx.

◆ GetValue()

Double_t TNeuron::GetValue ( ) const

Computes the output using the appropriate function and all the weighted inputs, or uses the branch as input.

In that case, the branch normalisation is also used.

Definition at line 944 of file TNeuron.cxx.

◆ GetWeight()

Double_t TNeuron::GetWeight ( ) const

inline

Definition at line 48 of file TNeuron.h.

◆ operator=()

TNeuron & TNeuron::operator= ( const TNeuron & )

private

◆ SetDEDw()

void TNeuron::SetDEDw ( Double_t in )

Sets the derivative of the total error wrt the neuron weight.

Definition at line 1164 of file TNeuron.cxx.

◆ SetNewEvent()

void TNeuron::SetNewEvent ( ) const

Inform the neuron that inputs of the network have changed, so that the buffered values have to be recomputed.

Definition at line 1153 of file TNeuron.cxx.

◆ SetNormalisation()

void TNeuron::SetNormalisation	(	Double_t	mean,
		Double_t	RMS
	)

Sets the normalization variables.

Any input neuron will return (branch-mean)/RMS. When UseBranch is called, mean and RMS are automatically set to the actual branch mean and RMS.

Definition at line 1133 of file TNeuron.cxx.

◆ SetWeight()

void TNeuron::SetWeight ( Double_t w )

Sets the neuron weight to w.

The neuron weight corresponds to the bias in the linear combination of the inputs.

Definition at line 1144 of file TNeuron.cxx.

◆ Sigmoid()

Double_t TNeuron::Sigmoid ( Double_t x ) const

protected

The Sigmoid.

Fast computation of the values of the sigmoid function. Uses values of the function up to the seventh order tabulated at 700 points. Values were computed in long double precision (16 bytes, precision to about 37 digits) on a hp computer. Some values were checked with Mathematica. Result should be correct to ~ 15 digits (about double precision)

From the mlpfit package (J.Schwindling 20-Jul-1999)

Definition at line 91 of file TNeuron.cxx.

◆ UseBranch()

TTreeFormula * TNeuron::UseBranch	(	TTree *	input,
		const char *	formula
	)

Sets a formula that can be used to make the neuron an input.

The formula is automatically normalized to mean=0, RMS=1. This normalisation is used by GetValue() (input neurons) and GetError() (output neurons)

Definition at line 874 of file TNeuron.cxx.

Friends And Related Symbol Documentation

◆ TSynapse

friend class TSynapse

friend

Definition at line 26 of file TNeuron.h.

Member Data Documentation

◆ fDeDw

Double_t TNeuron::fDeDw

private

! buffer containing the last derivative of the error

Definition at line 84 of file TNeuron.h.

◆ fDEDw

Double_t TNeuron::fDEDw

private

! buffer containing the sum over all examples of DeDw

Definition at line 85 of file TNeuron.h.

◆ fDerivative

Double_t TNeuron::fDerivative

private

! buffer containing the last neuron derivative

Definition at line 82 of file TNeuron.h.

◆ fExtD

TFormula* TNeuron::fExtD

private

derivative (external mode)

Definition at line 74 of file TNeuron.h.

◆ fExtF

TFormula* TNeuron::fExtF

private

function (external mode)

Definition at line 73 of file TNeuron.h.

◆ fFormula

TTreeFormula* TNeuron::fFormula

private

! formula to be used for inputs and outputs

Definition at line 75 of file TNeuron.h.

◆ fIndex

Int_t TNeuron::fIndex

private

! index in the formula

Definition at line 76 of file TNeuron.h.

◆ fInput

Double_t TNeuron::fInput

private

! buffer containing the last neuron input

Definition at line 78 of file TNeuron.h.

◆ flayer

TObjArray TNeuron::flayer

private

pointers to the current level in a network (neurons, not synapses)

Definition at line 69 of file TNeuron.h.

◆ fNewDeDw

Bool_t TNeuron::fNewDeDw

private

! do we need to compute fDeDw again ?

Definition at line 83 of file TNeuron.h.

◆ fNewDeriv

Bool_t TNeuron::fNewDeriv

private

! do we need to compute fDerivative again ?

Definition at line 81 of file TNeuron.h.

◆ fNewInput

Bool_t TNeuron::fNewInput

private

! do we need to compute fInput again ?

Definition at line 77 of file TNeuron.h.

◆ fNewValue

Bool_t TNeuron::fNewValue

private

! do we need to compute fValue again ?

Definition at line 79 of file TNeuron.h.

◆ fNorm

Double_t TNeuron::fNorm[2]

private

normalisation to mean=0, RMS=1.

Definition at line 71 of file TNeuron.h.

◆ fpost

TObjArray TNeuron::fpost

private

pointers to the next level in a network

Definition at line 68 of file TNeuron.h.

◆ fpre

TObjArray TNeuron::fpre

private

pointers to the previous level in a network

Definition at line 67 of file TNeuron.h.

◆ fType

ENeuronType TNeuron::fType

private

neuron type

Definition at line 72 of file TNeuron.h.

◆ fValue

Double_t TNeuron::fValue

private

! buffer containing the last neuron output

Definition at line 80 of file TNeuron.h.

◆ fWeight

Double_t TNeuron::fWeight

private

weight used for computation

Definition at line 70 of file TNeuron.h.

Libraries for TNeuron:

[legend]

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

tmva/tmva/inc/TMVA/TNeuron.h
math/mlp/src/TNeuron.cxx

Public Types

Public Member Functions

Protected Member Functions

Private Member Functions

Private Attributes

Friends

Additional Inherited Members

Member Enumeration Documentation

◆ ENeuronType

Constructor & Destructor Documentation

◆ TNeuron() [1/2]

◆ ~TNeuron()

◆ TNeuron() [2/2]

Member Function Documentation

◆ AddInLayer()

◆ AddPost()

◆ AddPre()

◆ DSigmoid()

◆ ForceExternalValue()

◆ GetBranch()

◆ GetDeDw()

◆ GetDEDw()

◆ GetDerivative()

◆ GetError()

◆ GetInLayer()

◆ GetInput()

◆ GetNormalisation()

◆ GetPost()

◆ GetPre()

◆ GetTarget()

◆ GetType()

◆ GetValue()

◆ GetWeight()

◆ operator=()

◆ SetDEDw()

◆ SetNewEvent()

◆ SetNormalisation()

◆ SetWeight()

◆ Sigmoid()

◆ UseBranch()

Friends And Related Symbol Documentation

◆ TSynapse

Member Data Documentation

◆ fDeDw

◆ fDEDw

◆ fDerivative

◆ fExtD

◆ fExtF

◆ fFormula

◆ fIndex

◆ fInput

◆ flayer

◆ fNewDeDw

◆ fNewDeriv

◆ fNewInput

◆ fNewValue

◆ fNorm

◆ fpost

◆ fpre

◆ fType

◆ fValue

◆ fWeight