Definition at line 44 of file TNeuron.h.

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

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

virtual	~TNeuron ()

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

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

Double_t	GetBranch () const
	Returns the formula value. More...

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

Double_t	GetDEDw () const

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

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

TNeuron *	GetInLayer (Int_t n) const

Double_t	GetInput () const
	Returns neuron input. More...

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. More...

ENeuronType	GetType () const
	Returns the neuron type. More...

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

Double_t	GetWeight () const

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

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

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

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

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

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. More...

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

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

Double_t	Sigmoid (Double_t x) const
	The Sigmoid. More...

Private Member Functions
	TNeuron (const TNeuron &)

TNeuron &	operator= (const TNeuron &)

Private Attributes
Double_t	fDeDw
	do we need to compute fDeDw again ? More...

Double_t	fDEDw
	buffer containing the last derivative of the error More...

Double_t	fDerivative
	do we need to compute fDerivative again ? More...

TFormula *	fExtD

TFormula *	fExtF

TTreeFormula *	fFormula

Int_t	fIndex
	formula to be used for inputs and outputs More...

Double_t	fInput
	do we need to compute fInput again ? More...

TObjArray	flayer

Bool_t	fNewDeDw
	buffer containing the last neuron derivative More...

Bool_t	fNewDeriv
	buffer containing the last neuron output More...

Bool_t	fNewInput
	index in the formula More...

Bool_t	fNewValue
	buffer containing the last neuron input More...

Double_t	fNorm [2]

TObjArray	fpost

TObjArray	fpre

ENeuronType	fType

Double_t	fValue
	do we need to compute fValue again ? More...

Double_t	fWeight

Friends
class	TSynapse

#include <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 48 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 51 of file TNeuron.cxx.

◆ ~TNeuron()

virtual TNeuron::~TNeuron ( )

inlinevirtual

Definition at line 53 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 857 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 846 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 834 of file TNeuron.cxx.

◆ DSigmoid()

Double_t TNeuron::DSigmoid ( Double_t x ) const

protected

The Derivative of the Sigmoid.

Definition at line 818 of file TNeuron.cxx.

◆ ForceExternalValue()

void TNeuron::ForceExternalValue ( Double_t value )

Uses the branch type to force an external value.

Definition at line 1125 of file TNeuron.cxx.

◆ GetBranch()

Double_t TNeuron::GetBranch ( ) const

Returns the formula value.

Definition at line 914 of file TNeuron.cxx.

◆ GetDeDw()

Double_t TNeuron::GetDeDw ( ) const

Computes the derivative of the error wrt the neuron weight.

Definition at line 1084 of file TNeuron.cxx.

◆ GetDEDw()

Double_t TNeuron::GetDEDw ( ) const

inline

Definition at line 72 of file TNeuron.h.

◆ GetDerivative()

Double_t TNeuron::GetDerivative ( ) const

computes the derivative for the appropriate function at the working point

Definition at line 1011 of file TNeuron.cxx.

◆ GetError()

Double_t TNeuron::GetError ( ) const

Computes the error for output neurons.

Returns 0 for other neurons.

Definition at line 1063 of file TNeuron.cxx.

◆ GetInLayer()

TNeuron* TNeuron::GetInLayer ( Int_t n ) const

inline

Definition at line 56 of file TNeuron.h.

◆ GetInput()

Double_t TNeuron::GetInput ( ) const

Returns neuron input.

Definition at line 925 of file TNeuron.cxx.

◆ GetNormalisation()

const Double_t* TNeuron::GetNormalisation ( ) const

inline

Definition at line 69 of file TNeuron.h.

◆ GetPost()

TSynapse* TNeuron::GetPost ( Int_t n ) const

inline

Definition at line 55 of file TNeuron.h.

◆ GetPre()

TSynapse* TNeuron::GetPre ( Int_t n ) const

inline

Definition at line 54 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 1074 of file TNeuron.cxx.

◆ GetType()

TNeuron::ENeuronType TNeuron::GetType ( ) const

Returns the neuron type.

Definition at line 867 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 948 of file TNeuron.cxx.

◆ GetWeight()

Double_t TNeuron::GetWeight ( ) const

inline

Definition at line 67 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 1168 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 1157 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 1137 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 1148 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 95 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 878 of file TNeuron.cxx.

Friends And Related Function Documentation

◆ TSynapse

friend class TSynapse

friend

Definition at line 45 of file TNeuron.h.

Member Data Documentation

◆ fDeDw

Double_t TNeuron::fDeDw

private

do we need to compute fDeDw again ?

Definition at line 105 of file TNeuron.h.

◆ fDEDw

Double_t TNeuron::fDEDw

private

buffer containing the last derivative of the error

Definition at line 106 of file TNeuron.h.

◆ fDerivative

Double_t TNeuron::fDerivative

private

do we need to compute fDerivative again ?

Definition at line 103 of file TNeuron.h.

◆ fExtD

TFormula* TNeuron::fExtD

private

Definition at line 93 of file TNeuron.h.

◆ fExtF

TFormula* TNeuron::fExtF

private

Definition at line 92 of file TNeuron.h.

◆ fFormula

TTreeFormula* TNeuron::fFormula

private

Definition at line 96 of file TNeuron.h.

◆ fIndex

Int_t TNeuron::fIndex

private

formula to be used for inputs and outputs

Definition at line 97 of file TNeuron.h.

◆ fInput

Double_t TNeuron::fInput

private

do we need to compute fInput again ?

Definition at line 99 of file TNeuron.h.

◆ flayer

TObjArray TNeuron::flayer

private

Definition at line 88 of file TNeuron.h.

◆ fNewDeDw

Bool_t TNeuron::fNewDeDw

private

buffer containing the last neuron derivative

Definition at line 104 of file TNeuron.h.

◆ fNewDeriv

Bool_t TNeuron::fNewDeriv

private

buffer containing the last neuron output

Definition at line 102 of file TNeuron.h.

◆ fNewInput

Bool_t TNeuron::fNewInput

private

index in the formula

Definition at line 98 of file TNeuron.h.

◆ fNewValue

Bool_t TNeuron::fNewValue

private

buffer containing the last neuron input

Definition at line 100 of file TNeuron.h.

◆ fNorm

Double_t TNeuron::fNorm[2]

private

Definition at line 90 of file TNeuron.h.

◆ fpost

TObjArray TNeuron::fpost

private

Definition at line 87 of file TNeuron.h.

◆ fpre

TObjArray TNeuron::fpre

private

Definition at line 86 of file TNeuron.h.

◆ fType

ENeuronType TNeuron::fType

private

Definition at line 91 of file TNeuron.h.

◆ fValue

Double_t TNeuron::fValue

private

do we need to compute fValue again ?

Definition at line 101 of file TNeuron.h.

◆ fWeight

Double_t TNeuron::fWeight

private

Definition at line 89 of file TNeuron.h.

Libraries for TNeuron:

[legend]

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

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

Public Types

Public Member Functions

Protected Member Functions

Private Member Functions

Private Attributes

Friends

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 Function Documentation

◆ TSynapse

Member Data Documentation

◆ fDeDw

◆ fDEDw

◆ fDerivative

◆ fExtD

◆ fExtF

◆ fFormula

◆ fIndex

◆ fInput

◆ flayer

◆ fNewDeDw

◆ fNewDeriv

◆ fNewInput

◆ fNewValue

◆ fNorm

◆ fpost

◆ fpre

◆ fType

◆ fValue

◆ fWeight