RNN遞歸神經網絡 C++實現

//讓程序自己學會是否需要進位，從而學會加法

#include "iostream"
#include "math.h"
#include "stdlib.h"
#include "time.h"
#include "vector"
#include "assert.h"
using namespace std;

#define innode  2       //輸入結點數，將輸入2個加數
#define hidenode  16    //隱藏結點數，存儲“攜帶位”
#define outnode  1      //輸出結點數，將輸出一個預測數字
#define alpha  0.1      //學習速率
#define binary_dim 8    //二進制數的最大長度

#define randval(high) ( (double)rand() / RAND_MAX * high )
#define uniform_plus_minus_one ( (double)( 2.0 * rand() ) / ((double)RAND_MAX + 1.0) - 1.0 )  //均勻隨機分布


int largest_number = ( pow(2, binary_dim) );  //跟二進制最大長度對應的可以表示的最大十進制數

//激活函數
double sigmoid(double x) 
{
    return 1.0 / (1.0 + exp(-x));
}

//激活函數的導數，y為激活函數值
double dsigmoid(double y)
{
    return y * (1 - y);  
}           
//將一個10進制整數轉換為2進制數
void int2binary(int n, int *arr)
{
    int i = 0;
    while(n)
    {
        arr[i++] = n % 2;
        n /= 2;
    }
    while(i < binary_dim)
        arr[i++] = 0;
}

class RNN
{
public:
    RNN();
    virtual ~RNN();
    void train();

public:
    double w[innode][hidenode];        //連接輸入層與隱藏層的權值矩陣
    double w1[hidenode][outnode];      //連接隱藏層與輸出層的權值矩陣
    double wh[hidenode][hidenode];     //連接前一時刻的隱含層與現在時刻的隱含層的權值矩陣

    double *layer_0;       //layer 0 輸出值，由輸入向量直接設定
    //double *layer_1;     //layer 1 輸出值
    double *layer_2;       //layer 2 輸出值
};

void winit(double w[], int n) //權值初始化
{
    for(int i=0; i layer_1_vector;      //保存隱藏層
    vector layer_2_delta;        //保存誤差關於Layer 2 輸出值的偏導

    for(epoch=0; epoch<11000; epoch++)  //訓練次數
    {
        double e = 0.0;  //誤差
        for(i=0; i=0 ; p--)
        {
            layer_0[0] = a[p];
            layer_0[1] = b[p];

            layer_1 = layer_1_vector[p+1];     //當前隱藏層
            double *layer_1_pre = layer_1_vector[p];   //前一個隱藏層

            for(k=0; k=0; k--)
                cout << d[k];
            cout << endl;

            cout << "true：" ;
            for(k=binary_dim-1; k>=0; k--)
                cout << c[k];
            cout << endl;

            int out = 0;
            for(k=binary_dim-1; k>=0; k--)
                out += d[k] * pow(2, k);
            cout << a_int << " + " << b_int << " = " << out << endl << endl;
        }
    }
}


int main()
{
    srand(time(NULL));
    RNN rnn;
    rnn.train();
    return 0;
}

參考：
http://blog.csdn.net/zzukun/article/details/49968129
http://www.cnblogs.com/wb-DarkHorse/archive/2012/12/12/2815393.html