40 lines
1.1 KiB
C++
40 lines
1.1 KiB
C++
#pragma once
|
|
|
|
#include <cmath>
|
|
|
|
#include "./ActivationFunction.h"
|
|
|
|
namespace NeuralNetwork {
|
|
namespace ActivationFunction {
|
|
|
|
/**
|
|
* @author Tomas Cernik (Tom.Cernik@gmail.com)
|
|
* @brief Class for computing sigmoid
|
|
*/
|
|
class Sigmoid: public ActivationFunction {
|
|
public:
|
|
Sigmoid(const float lambdaP = -0.5): lambda(lambdaP) {}
|
|
|
|
|
|
inline virtual float derivatedOutput(const float &, const float &output) const override { return -lambda*output*(1.0f-output); }
|
|
inline virtual float operator()(const float &x) const override { return 1.0f / (1.0f +exp(lambda*x) ); };
|
|
|
|
virtual ActivationFunction* clone() const override {
|
|
return new Sigmoid(lambda);
|
|
}
|
|
|
|
virtual SimpleJSON::Type::Object serialize() const override {
|
|
return {{"class", "NeuralNetwork::ActivationFunction::Sigmoid"}, {"lambda", lambda}};
|
|
}
|
|
|
|
static std::unique_ptr<Sigmoid> deserialize(const SimpleJSON::Type::Object &obj) {
|
|
return std::unique_ptr<Sigmoid>(new Sigmoid(obj["lambda"].as<double>()));
|
|
}
|
|
|
|
protected:
|
|
float lambda;
|
|
|
|
NEURAL_NETWORK_REGISTER_ACTIVATION_FUNCTION(NeuralNetwork::ActivationFunction::Sigmoid, Sigmoid::deserialize)
|
|
};
|
|
}
|
|
} |