A Deep Learning Method Combined Sparse Autoencoder with SVM

In this paper, a novel unsupervised method for learning sparse features combined with support vector machines for classification is proposed. The classical SVM method has restrictions on the large-scale applications. This model uses sparse auto encoder, a deep learning algorithm, to improve the performance. Firstly, we use multiple layers of sparse auto encoder to learn the features of the data. Secondly, we use SVM to classify. Many experimental results show that compared with SVM, our proposed method can improve the classification rate. In particular, it can effectively deal with large-scale data sets.