Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/SMC.2018.00718 | 2018 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC) |
Keywords | Field | DocType |
Autoencoder, Pseudoinverse learning algorithm, Receptive function, Broad learning | Gradient descent,Autoencoder,Pattern recognition,Computer science,Moore–Penrose pseudoinverse,Artificial intelligence,Initial value problem,High dimensional space,Deep neural networks,Machine learning | Conference |
ISSN | Citations | PageRank |
1062-922X | 0 | 0.34 |
References | Authors | |
0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bingxin Xu | 1 | 97 | 7.60 |
Ping Guo | 2 | 601 | 85.05 |