#pragma once

#include <cmath>

#include "./StreamingActivationFunction.h"
#include "../../sse_mathfun.h"

namespace NeuralNetwork {
namespace ActivationFunction {

	/**
	* @author Tomas Cernik (Tom.Cernik@gmail.com)
	* @brief Class for computing sigmoid
	*/
	class Sigmoid: public StreamingActivationFunction {
		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) ); };

			inline virtual __m128 operator()(const __m128 &x) const override {
				// exp_ps is extremly slow!
				return _mm_div_ps(_mm_set1_ps(1.0),_mm_add_ps(exp_ps(_mm_mul_ps(_mm_set1_ps(lambda),x)),_mm_set1_ps(1.0)));
			}

			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)
	};
}
}