点击次数：

论文类型：期刊论文

发表时间：2018-01-01

发表刊物：NEURAL NETWORK WORLD

收录刊物：SCIE

卷号：28

期号：2

页面范围：133-147

ISSN号：1210-0552

关键字：autoencoder; sparse representation; unsupervised feature learning; deep network; L-1/2 regularization

摘要：Autoencoder networks have been demonstrated to be efficient for unsupervised learning of representation of images, documents and time series. Sparse representation can improve the interpretability of the input data and the generalization of a model by eliminating redundant features and extracting the latent structure of data. In this paper, we use L-1/2 regularization method to enforce sparsity on the hidden representation of an autoencoder for achieving sparse representation of data. The performance of our approach in terms of unsupervised feature learning and supervised classification is assessed on the MNIST digit data set, the ORL face database and the Reuters-21578 text corpus. The results demonstrate that the proposed autoencoder can produce sparser representation and better reconstruction performance than the Sparse Autoencoder and the L-1 regularization Autoencoder. The new representation is also illustrated to be useful for a deep network to improve the classification performance.