【deep learning学习笔记】注释yusugomori的RBM代码 --- cpp文件 -- 准备工作

一些辅助函数，做模型的准备工作。

#include <iostream>
#include <math.h>
#include "RBM.h"
using namespace std;

// To generate a value between min and max in a uniform distribution
double uniform(double min, double max) 
{
  return rand() / (RAND_MAX + 1.0) * (max - min) + min;
}

// To get the result of n-binomial test by the p probability
int binomial(int n, double p) 
{
  if(p < 0 || p > 1) return 0;
  
  int c = 0;
  double r;
  
  for(int i=0; i<n; i++) {
    r = rand() / (RAND_MAX + 1.0);
    if (r < p) c++;
  }

  return c;
}

// To get the result of sigmoid function
double sigmoid(double x) 
{
  return 1.0 / (1.0 + exp(-x));
}

// To initialize the parameter of RBM
RBM::RBM (int size, int n_v, int n_h, double **w, double *hb, double *vb) {
  N = size;			// the number of training samples
  n_visible = n_v;	// the number of visiable node
  n_hidden = n_h;	// the number of hidden node

  if(w == NULL) 
  {
	// W[hiddenNode][visiableNode]
    W = new double*[n_hidden];
    for(int i=0; i<n_hidden; i++) 
		W[i] = new double[n_visible];
	// the range of initial value of W
	// some better method is proposed by another doc
    double a = 1.0 / n_visible;

    for(int i=0; i<n_hidden; i++) 
	{
      for(int j=0; j<n_visible; j++) 
	  {
		// set the initial value in a uniform distribution of [-a, a]
        W[i][j] = uniform(-a, a);
      }
    }
  } else 
  {
    W = w;
  }

  // the bias for hidden node
  if(hb == NULL) 
  {
    hbias = new double[n_hidden];
    for(int i=0; i<n_hidden; i++) 
		hbias[i] = 0;
  } else 
  {
    hbias = hb;
  }

  // the bias for visiable node
  if(vb == NULL) 
  {
    vbias = new double[n_visible];
    for(int i=0; i<n_visible; i++) 
		vbias[i] = 0;
  } else 
  {
    vbias = vb;
  }
} // RBM::RBM

// destructor to release the memory
RBM::~RBM() 
{
  for(int i=0; i<n_hidden; i++) 
	  delete[] W[i];
  delete[] W;
  delete[] hbias;
  delete[] vbias;
}