#ifndef MLPP_WGAN_H #define MLPP_WGAN_H // // WGAN.hpp // // Created by Marc Melikyan on 11/4/20. // #include "../hidden_layer/hidden_layer.h" #include "../output_layer/output_layer.h" #include #include #include class MLPPWGAN { public: MLPPWGAN(real_t k, std::vector> outputSet); ~MLPPWGAN(); std::vector> generateExample(int n); void gradientDescent(real_t learning_rate, int max_epoch, bool UI = 1); real_t score(); void save(std::string fileName); void addLayer(int n_hidden, std::string activation, std::string weightInit = "Default", std::string reg = "None", real_t lambda = 0.5, real_t alpha = 0.5); void addOutputLayer(std::string weightInit = "Default", std::string reg = "None", real_t lambda = 0.5, real_t alpha = 0.5); private: std::vector> modelSetTestGenerator(std::vector> X); // Evaluator for the generator of the WGAN. std::vector modelSetTestDiscriminator(std::vector> X); // Evaluator for the discriminator of the WGAN. real_t Cost(std::vector y_hat, std::vector y); void forwardPass(); void updateDiscriminatorParameters(std::vector>> hiddenLayerUpdations, std::vector outputLayerUpdation, real_t learning_rate); void updateGeneratorParameters(std::vector>> hiddenLayerUpdations, real_t learning_rate); std::tuple>>, std::vector> computeDiscriminatorGradients(std::vector y_hat, std::vector outputSet); std::vector>> computeGeneratorGradients(std::vector y_hat, std::vector outputSet); void UI(int epoch, real_t cost_prev, std::vector y_hat, std::vector outputSet); std::vector> outputSet; std::vector y_hat; std::vector network; MLPPOldOutputLayer *outputLayer; int n; int k; }; #endif /* WGAN_hpp */