class TNeuron: public TObject
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 The SetNewEvent() method is there to inform buffered values are outdated.
Function Members (Methods)
public:
protected:
| virtual void | TObject::DoError(int level, const char* location, const char* fmt, va_list va) const |
| void | TObject::MakeZombie() |
private:
| void | DeleteLinksArray(TObjArray*& links) |
| void | InitNeuron() |
| TMVA::MsgLogger& | Log() const |
| void | NullifyLinks(TObjArray*& links) |
| Int_t | NumLinks(TObjArray* links) const |
| void | PrintLinks(TObjArray* links) const |
| void | PrintMessage(TMVA::EMsgType, TString message) |
Data Members
public:
| enum TObject::EStatusBits { | kCanDelete | |
| kMustCleanup | ||
| kObjInCanvas | ||
| kIsReferenced | ||
| kHasUUID | ||
| kCannotPick | ||
| kNoContextMenu | ||
| kInvalidObject | ||
| }; | ||
| enum TObject::[unnamed] { | kIsOnHeap | |
| kNotDeleted | ||
| kZombie | ||
| kBitMask | ||
| kSingleKey | ||
| kOverwrite | ||
| kWriteDelete | ||
| }; |
private:
| TMVA::TActivation* | fActivation | activation equation |
| Double_t | fActivationValue | activation/output value |
| Double_t | fDEDw | sum of all deltas |
| Double_t | fDelta | error field of neuron |
| Double_t | fError | error, only set for output neurons |
| Bool_t | fForcedValue | flag for forced input value |
| TMVA::TNeuronInput* | fInputCalculator | input calculator |
| TObjArray* | fLinksIn | array of input synapses |
| TObjArray* | fLinksOut | array of output synapses |
| TMVA::MsgLogger* | fLogger | ! message logger |
| Double_t | fValue | input value |
Class Charts
Function documentation
TNeuron(TNeuron::ENeuronType type /*= kSigmoid*/, const char* name /*= ""*/, const char* title /*= ""*/, const char* extF /*= ""*/, const char* extD /*= ""*/ )
Usual constructor
Double_t 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.
TNeuron(ENeuronType type = kSigmoid, const char* name = "", const char* title = "", const char* extF = "", const char* extD = "" )
{}