The base class for all activation functions in neural network. More...
#include <GeneralActivationFunction.h>
Public Member Functions | |
| virtual double | CalcOutput (const double input)=0 |
| The function that maps between the weighted sum that's the input of the neuron and the output. More... | |
| virtual double | CalcDeriv (const double input)=0 |
| The derivative of the function defined in CalcOutput. More... | |
| GeneralActivationFunction () | |
| virtual | ~GeneralActivationFunction () |
Detailed Description
The base class for all activation functions in neural network.
The activation function in a neural network node determines the type of non-linearity between input and output. We have to implement the activation function and its derivative.
Definition at line 15 of file GeneralActivationFunction.h.
Constructor & Destructor Documentation
| gplib::GeneralActivationFunction::GeneralActivationFunction | ( | ) |
Definition at line 5 of file GeneralActivationFunction.cpp.
|
virtual |
Definition at line 8 of file GeneralActivationFunction.cpp.
Member Function Documentation
|
pure virtual |
The derivative of the function defined in CalcOutput.
Implemented in gplib::BipolarActivationFunction, and gplib::IdentityActivationFunction.
|
pure virtual |
The function that maps between the weighted sum that's the input of the neuron and the output.
Implemented in gplib::BipolarActivationFunction, and gplib::IdentityActivationFunction.
The documentation for this class was generated from the following files:
