百度了半天yusugomori，也不知道他是谁。不过这位老兄写了deep learning的代码，包括RBM、逻辑回归、DBN、autoencoder等，实现语言包括c、c++、java、python等。是学习的好材料。代码下载地址：https://github.com/yusugomori/DeepLearning。不过这位老兄不喜欢写注释，而且这些模型的原理、公式什么的，不了解的话就看不懂代码。我从给他写注释开始，边看资料、边理解它的代码、边给他写上注释。
工具包中RBM的实现包含了两个文件，RBM.h和RBM.cpp。RBM.h添加注释后，如下：
class RBM
{
public:
// the number of training sample
int N;
// the number of visiable node
int n_visible;
// the number of hidden node
int n_hidden;
// the weight connecting the visiable node and the hidden node
double **W;
// the bias of hidden node
double *hbias;
// the bias of visiable node
double *vbias; public:
// construct the RBM by input parameters
RBM (int, // N
int, // n_visible
int, // n_hidden
double**, // W
double*, // hbias
double* // vbias
);
// destructor, release all the memory of parameters
~RBM ();
// CD-k algorithm to train RBM
void contrastive_divergence (int*, // one input sample
double, // the learning rate
int // the k of CD-k, it is usually 1
); // these the functions of Gibbs sample // sample the hidden node given the visiable node, 'sample' means calculating
// 1. the output probability of the hidden node given the input of visiable node
// and the weight of current RBM; 2. the 0-1 state of hidden node by a binomial
// distribution given the calculated output probability of this hidden node
void sample_h_given_v (int*, // one input sample from visiable nodes -- input
double*, // the output probability of hidden nodes -- output
int* // the calculated 0-1 state of hidden node -- output
);
// sample the visiable node given the hidden node, 'sample' means calculating
// 1. the output probability of the visiable node given the input of hidden node
// and the weight of current RBM; 2. the 0-1 state of visiable node by a binomial
// distribution given the calculated output probability of this visiable node
void sample_v_given_h (int*, // one input sample from hidden nodes -- input
double*, // the output probability of visiable nodes -- output
int* // the calculated 0-1 state of visiable node -- output
);
// 'propup' -- probability up. It's called by the 'sample_x_given_x' function and the reconstruct funciton
// To calculate the probability in 'upper' node given the input from 'lower' node in RBM
// note: what is the 'up' and 'down'? the visiable node is below (down) the hidden node.
// 'probability up' means calculating the probability of hidden node given the visiable node
// return value: the output probability of the hidden node given the input of visiable node
// and the weight of current RBM
// the probability is : p (hi|v) = sigmod ( sum_j(vj * wij) + bi)
double propup (int*, // one input sample from visiable node -- input
double*, // the weight W connecting one hidden node to all visible node -- input
double // the bias for this hidden node -- input
);
// 'propdown' -- probability down. It's called by the 'sample_x_given_x' function and the reconstruct funciton
// To calculate the probability in 'lower' node given the input from 'upper' node in RBM
// note: what is the 'up' and 'down'? the visiable node is below (down) the hidden node.
// 'probability down' means calculating the probability of visiable node given the hidden node
// return value: the output probability of the visiable node given the input of hidden node
// and the weight of current RBM
// the probability is : p (vi|h) = sigmod ( sum_j(hj * wij) + ci)
double propdown (int*, // one input sample from hidden node -- input
int, // the index of visiable node in the W matrix -- input
double // the bias for this visible node -- input
);
// 'gibbs_hvh' -- gibbs sample firstly from hidden node to visible node, then sample
// from visiable node to hidden node. It is called by contrastive_divergence.
void gibbs_hvh (int*, // one input sample from hidden node, h0 -- input
double*, // the output probability of visiable nodes -- output
int*, // the calculated 0-1 state of visiable node -- output
double*, // the output probability of reconstructed hidden node h1 -- output
int* // the calculated 0-1 state of reconstructed hidden node h1 -- output
);
// reconstruct the input visiable node by the trained RBM (so as to varify the RBM model)
void reconstruct (int*, // one input sample from visiable node
double* // the reconstructed output by RBM model
);
};
主要添加了函数说明、参数说明、计算说明、调用关系等。