The conventional Deep Belief Network (DBN) often utilizes the method of randomly initializing the weights and bias of Restricted Boltzmann Machine(RBM) to initialize the network. Although it could overcome the problems of local optimality and long training time to some extent, it is still difficult to further achieve higher accuracy and better learning efficiency owing to the huge difference between reconstruction and original input resulting from random initialization. In view of the above-mentioned problem, a kind of DBN model based on Sparse Denoising AutoEncoder (SDAE) was proposed. The advantage of the advocated model was the feature extraction by SDAE. Firstly, SDAE was trained, and then, the obtained weights and bias were utilized to initialize DBN. Finally, DBN was trained. Experiments were performed on card game data set of Poker hand and handwriting data sets of MNIST and USPS to verify the performance of the proposed model. In Poker hand data set, compared with the conventional DBN, the error rate of the proposed model is lowered by 46.4%, the accuracy rate and the recall rate are improved by 15.56% and 14.12% respectively. The results exhibit that the proposed method is superior to other existing methods in recognition performance.

The association rules generated by traditional algorithms have the shortcomings of few classes and low correlation. Based on the analysis of these shortcomings, and combined with Spearman rank correlation coefficient, a new multi-class association rule algorithm was proposed. Based on the strong association rules generated by traditional algorithms, the new algorithm used Spearman rank correlation to calculate the synchronous and asynchronous correlation coefficient. Setting the correlation coefficient as the interest threshold, the new algorithm can generate synchronous positive rules, contrary positive rules, synchronous negative rules and contrary negative rules. Experiment has been carried out to illustrate the effectiveness and superiority of the algorithm.