#pragma once

#include <vector>
#include <cmath>

#include <NeuralNetwork/FeedForward/Network.h>
#include "BackPropagation.h"

namespace NeuralNetwork {
	namespace Learning {

		/** @class QuickPropagation
		 * @brief
		 */
		class QuickPropagation : public BackPropagation {

		public:
			inline QuickPropagation(FeedForward::Network &feedForwardNetwork, CorrectionFunction::CorrectionFunction *correction = new CorrectionFunction::Linear()):
				BackPropagation(feedForwardNetwork,correction),previousSlopes() {
				resize();
			}

			virtual ~QuickPropagation() {
			}

		protected:
			float _maxChange=1.75;
			float _epsilon=0.5;

			virtual inline void resize() override {
				if(slopes.size()!=network.size())
					slopes.resize(network.size());

				for(std::size_t i=0; i < network.size(); i++) {
					if(slopes[i].size()!=network[i].size())
						slopes[i].resize(network[i].size());
				}

				if(previousSlopes.size()!=network.size())
					previousSlopes.resize(network.size());

				for(std::size_t i=0; i < network.size(); i++) {
					if(previousSlopes[i].size()!=network[i].size())
						previousSlopes[i].resize(network[i].size());

					for(std::size_t j=0; j < previousSlopes[i].size(); j++) {
						previousSlopes[i][j]=1.0;
					}
				}

				if(lastWeightChange.size()!=network.size())
					lastWeightChange.resize(network.size());

				for(std::size_t i=0; i < network.size(); i++) {
					if(lastWeightChange[i].size()!=network[i].size())
						lastWeightChange[i].resize(network[i].size());

					for(std::size_t j=0; j < previousSlopes[i].size(); j++) {
						lastWeightChange[i][j]=1.0;
					}
				}
				weightChange= lastWeightChange;
			}

			virtual void updateWeights(const std::vector<float> &input) override;

			std::vector<std::vector<float>> previousSlopes ={};
			std::vector<std::vector<float>> lastWeightChange ={};
			std::vector<std::vector<float>> weightChange ={};
		};
	}
}