Abstract
In order to solve the problem of long training time that the Stacked Denoising Auto Encoder (SDAE) has. A kind of new SDAE is proposed which is based on adaptive learning rate and additional momentum term (LMSDAE). Finally, the LMSDAE is tested by Chinese News Text. The experimental results show that compared with the other three algorithms: SDAE, Sparse Denoising Auto Encoder (SPDAE) and Deep Belief Nets (DBN), the LMSDAE algorithm reduced the training times and increased the convergence rate. The accuracy of text classification can reach 87.95%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Zhao, J., Li, J., Zheng, R.: Application of adaptive learning rate method in power transformer fault diagnosis. J. Jilin Univ. (Inf. Sci. Ed.) 4, 415–420 (2008)
Jia, W., Li, M., Zhu, M., Wang, J.: License plate character recognition based on stacked denoising autoencoder. Comput. Eng. Des. 37(03), 751–756 (2016)
Ma, Y., Huo, Z., Yang, Z.: The implementation of the improved BP algorithm by adding the item of the momentum. Sci-Tech Inf. Dev. Econ. 8, 157–158 (2006)
Qiao, J., Wang, G., Li, X., Han, H., Chai, W.: Design and application of deep belief network with adaptive learning rate. Acta Automatica Sin. 43(8), 1339–1349 (2017)
Qiu, S., Jing, M., Zhang, Z., Lu, Y., Pei, Z.: Chinese short text classification based on denoising auto encoder. J. Inner Mongolia Univ. Natl. (Nat. Sci.) 5, 400–405 (2017)
Vincent, P., Larochelle, H., Bengio, Y.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning, Helsinki, Finland (2008)
Zhang, C., Jiang, J.: Study on sparse de-noising auto-encoder neural network. J. Inner Mongolia Univ. Natl. (Nat. Chin. Ed.) 31(1), 21–25 (2016)
Acknowledgements
This work is supported by the National Natural Science Foundation of China (61373067, 61672301), the Science and Technology Innovation Guide Project of Inner Mongolia Autonomous Region of china (KJCX2016, KJCX2017); the Information of Mongolian Medicine Based on Machine Learning Algorithm (MDXK004), the Research Program of science and technology at Universities of Inner Mongolia Autonomous Region (NJZY16177), the Natural Science Foundation of Inner Mongolia Autonomous Region of china (2016MS0624).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Qiu, S., Jiang, M., Zhang, Z., Lu, Y., Pei, Z. (2018). Chinese News Text Classification of the Stacked Denoising Auto Encoder Based on Adaptive Learning Rate and Additional Momentum Item. In: Huang, T., Lv, J., Sun, C., Tuzikov, A. (eds) Advances in Neural Networks – ISNN 2018. ISNN 2018. Lecture Notes in Computer Science(), vol 10878. Springer, Cham. https://doi.org/10.1007/978-3-319-92537-0_66
Download citation
DOI: https://doi.org/10.1007/978-3-319-92537-0_66
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-92536-3
Online ISBN: 978-3-319-92537-0
eBook Packages: Computer ScienceComputer Science (R0)