Image recognition based on improved convolutional deep belief network model

Aiming at the homogeneity of convolution kernels in Convolutional Deep Belief Network (CDBN), a cross-entropy-based sparse penalty mechanism suitable for Convolutional Restricted Boltzmann Machine (CRBM) model is introduced which makes the hidden layer units of the whole network in a lower activation state. On this basis, a parameter learning algorithm is applied to compensate the gradient by introducing the prior information of the samples, which alternates the supervised learning and unsupervised learning. The experimental results show that the proposed model can weaken the homogeneity of convolution kernels and improve the supervising and predicting ability of the network. The recognition rate on simulated dataset achieves 97.45%, which is increased 5.12% and 1.29% than Convolutional Neural Network (CNN) and the traditional CDBN model, respectively. At the same time, test error rate on common dataset MNIST also shows that the proposed model is more effective than some other state-of-the-art deep learning models.