A novel deep model for image recognition
Ming Lei Zhu, Yan Xiang Wu · 2014
In this paper we propose a hybrid deep network for image recognition. First we use the sparse autoencoder(SAE) which is a method to extract high-level feature representations of data in an unsupervised way, without any manual feature engineering, and then we perform the classification using the deep belief networks(DBNs), which consist of restricted Boltzmann machine(RBM). Finally, we implement some comparative experiments on image datasets, and the results show that our methods achieved better performance when compared with neural network and other deep learning techniques such as DBNs.