文献类型：期刊文献

英文题名：Broad and Pseudoinverse Learning for Autoencoder

作者：Xu, Bingxin[1]; Guo, Ping[2]

第一作者：徐冰心

机构：[1] Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, 100101, China; [2] Image Pro. and Patt. Recog. Lab, School of Systems Science, Beijing Normal University, Beijing, 100875, China

第一机构：北京联合大学北京市信息服务工程重点实验室

年份：2018

起止页码：4243-4247

外文期刊名：Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018

收录：EI(收录号：20191006582847)

语种：英文

外文关键词：Gradient methods - Deep neural networks

摘要：Autoencoder is one approach to automatically learn features from unlabeled data and received significant attention during the development of deep neural networks. However, the learning algorithm of autoencoder suffers from slow learning speed because of gradient descent based algorithms have many drawbacks. Pseudoinverse learning algorithm is a fast and fully automated method to train autoencoders. While when the dimension of data is far less than the number of data, the pseudoinverse learning can only obtain the optimal initial value of the autoencoder network and need further learning to achieve satisfactory results. In order to overcome the shortcomings mentioned above, we present a broad learning strategy to transform the input space to the high dimensional space through receptive function in this paper. The transformed data can be more suitable to pseudoinverse learning algorithm which can be obtained the accurate results of autoencoder efficiently. The experimental results show that the proposed method can achieve a comprehensively better performance in terms of training autoencoder efficiency and accuracy. ? 2018 IEEE.