Table 1 Algorithm description of train deep belief network.

Input: Data D = {x}, desired layers K and nodes number for each layer N _i

Output: The structure and learned initialization parameters of the DNN.

1. Learn parameters θ₁ for the 1^st layer RBM from data.

For k = 2:K

2. Initialize the k-th layer RBM by unroll the k-1th layer RBM to the kth layer, of which parameters $W_k=W_{k-1}^T$

3. Refine the parameters of kth layer RBM from data vectors generated from k-1th layer.

Return: Structure and parameters of the stacked RBMs.