library: libMLP
#include "TNeuron.h" |
TNeuron
class description - header file - source file - inheritance tree (.pdf)
protected:
void AddPost(TSynapse*)
void AddPre(TSynapse*)
Double_t DSigmoid(Double_t x) const
Double_t Sigmoid(Double_t x) const
public:
TNeuron(TNeuron::NeuronType type = kSigmoid, const char* name = "", const char* title = "", const char* extF = "", const char* extD = "")
TNeuron(const TNeuron&)
virtual ~TNeuron()
void AddInLayer(TNeuron*)
static TClass* Class()
void ForceExternalValue(Double_t value)
Double_t GetBranch() const
Double_t GetDeDw() const
Double_t GetDEDw() const
Double_t GetDerivative() const
Double_t GetError() const
TNeuron* GetInLayer(Int_t n) const
Double_t GetInput() const
const Double_t* GetNormalisation() const
TSynapse* GetPost(Int_t n) const
TSynapse* GetPre(Int_t n) const
Double_t GetTarget() const
TNeuron::NeuronType GetType() const
Double_t GetValue() const
Double_t GetWeight() const
virtual TClass* IsA() const
void SetDEDw(Double_t in)
void SetNewEvent() const
void SetNormalisation(Double_t mean, Double_t RMS)
void SetWeight(Double_t w)
virtual void ShowMembers(TMemberInspector& insp, char* parent)
virtual void Streamer(TBuffer& b)
void StreamerNVirtual(TBuffer& b)
TTreeFormula* UseBranch(TTree*, const char*)
private:
TObjArray fpre pointers to the previous level in a network
TObjArray fpost pointers to the next level in a network
TObjArray flayer pointers to the current level in a network (neurons, not synapses)
Double_t fWeight weight used for computation
Double_t fNorm[2] normalisation to mean=0, RMS=1.
TNeuron::NeuronType fType neuron type
TFormula* fExtF function (external mode)
TFormula* fExtD derivative (external mode)
TTreeFormula* fFormula ! formula to be used for inputs and outputs
Int_t fIndex ! index in the formula
Bool_t fNewInput ! do we need to compute fInput again ?
Double_t fInput ! buffer containing the last neuron input
Bool_t fNewValue ! do we need to compute fValue again ?
Double_t fValue ! buffer containing the last neuron output
Bool_t fNewDeriv ! do we need to compute fDerivative again ?
Double_t fDerivative ! buffer containing the last neuron derivative
Bool_t fNewDeDw ! do we need to compute fDeDw again ?
Double_t fDeDw ! buffer containing the last derivative of the error
Double_t fDEDw ! buffer containing the sum over all examples of DeDw
public:
static const TNeuron::NeuronType kOff
static const TNeuron::NeuronType kLinear
static const TNeuron::NeuronType kSigmoid
static const TNeuron::NeuronType kTanh
static const TNeuron::NeuronType kGauss
static const TNeuron::NeuronType kSoftmax
static const TNeuron::NeuronType kExternal
TNeuron
This class decribes 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.
Double_t Sigmoid(Double_t x)
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)
void AddPre(TSynapse * pre)
Adds a synapse to the neuron as an input
This method is used by the TSynapse while
connecting two neurons.
void AddPost(TSynapse * post)
Adds a synapse to the neuron as an output
This method is used by the TSynapse while
connecting two neurons.
void AddInLayer(TNeuron * nearP)
Tells a neuron which neurons form its layer (including itself).
This is needed for self-normalizing functions, like Softmax.
TTreeFormula* 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)
Double_t GetValue()
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.
Double_t GetError()
Computes the error for output neurons.
Returns 0 for other neurons.
Double_t GetTarget()
Computes the normalized target pattern for output neurons.
Returns 0 for other neurons.
Double_t GetDeDw()
Computes the derivative of the error wrt the neuron weight.
void 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.
void SetWeight(Double_t w)
Sets the neuron weight to w.
The neuron weight corresponds to the bias in the
linear combination of the inputs.
void SetNewEvent()
Inform the neuron that inputs of the network have changed,
so that the buffered values have to be recomputed.
void SetDEDw(Double_t in)
Sets the derivative of the total error wrt the neuron weight.
TNeuron(NeuronType type = kSigmoid, const char* name = "", const char* title = "", const char* extF = "", const char* extD = "" )
Author: Christophe.Delaere@cern.ch 20/07/03
Last update: root/mlp:$Name: $:$Id: TNeuron.cxx,v 1.20 2006/05/26 15:13:02 rdm Exp $
Copyright (C) 1995-2003, Rene Brun and Fons Rademakers. *
ROOT page - Class index - Class Hierarchy - Top of the page
This page has been automatically generated. If you have any comments or suggestions about the page layout send a mail to ROOT support, or contact the developers with any questions or problems regarding ROOT.