mlpackRNNTest

int main(int argc, char** argv) {

    arma::mat data, labels, prediction;
    size_t HiddenLayerSize, InputLayerSize, error;
    double ClassificationError;

    data.load("snpdata.csv");
    labels = data.col(0);
    data.shed_col(0);

    InputLayerSize = data.n_rows;
    HiddenLayerSize = data.n_rows + (data.n_rows / 2);

    LinearLayer<> linearLayer0(InputLayerSize, HiddenLayerSize);
    RecurrentLayer<> recurrentLayer0(HiddenLayerSize);
    BaseLayer<LogisticFunction> inputBaseLayer;

    LinearLayer<> hiddenLayer(HiddenLayerSize, 1);
    BaseLayer<LogisticFunction> hiddenBaseLayer;

    BinaryClassificationLayer classOutputLayer;

    auto modules = std::tie(linearLayer0, recurrentLayer0, inputBaseLayer,
                            hiddenLayer, hiddenBaseLayer);

    RNN<decltype(modules), BinaryClassificationLayer, RandomInitialization,
            MeanSquaredErrorFunction> NN(modules, classOutputLayer);

    SGD<decltype(NN)> opt(NN, 0.01, 100000, 1e-5, true);

    NN.Train(data, labels, opt);
    /*
    NN.Predict(data, prediction);

    error = 0;
    for (size_t i = 0; i < labels.n_rows; i++)
    {
        if (arma::sum(arma::sum(arma::abs(prediction.col(i) - labels.col(i)))) == 0)
            error++;
    }

    ClassificationError = error / (double) labels.n_rows * 100;

    cout << "Classification Error: " << ClassificationError << '\n';*/

    return 0;
}