learn.cu

__global__ void kFit(	const float* X, const int X_w, const int X_h, const float* y, const int y_w, float* l1, const int l1_w, float* l_1_d, float* pred, float* pred_d, float* W0, float* W1, float* buffer) {
	for (unsigned i = 0; i < 50; ++i) {
        dSigmoid(dDot(X, W0, l1, X_h, X_w, l1_w), l1, X_h, l1_w);
        dSigmoid(dDot(l1, W1, pred, X_h, l1_w, y_w), pred, X_h, y_w);
        dMartixByMatrixElementwise(dMartixSubstractMatrix(y, pred, pred_d, X_h, y_w), dSigmoid_d(pred, buffer, X_h, y_w), pred_d, X_h, y_w );
        dMartixByMatrixElementwise(dDot_m1_m2T(pred_d, W1, l_1_d, X_h, y_w, l1_w), dSigmoid_d(l1, buffer, X_h, l1_w), l_1_d, X_h, l1_w);
        dDot_m1T_m2( l1, pred_d, W1, X_h, l1_w, y_w );
        dDot_m1T_m2( X, l_1_d, W0, X_h, X_w, l1_w );
    }
}