Abstract
Traditional Deep Belief Networks (DBN) is prone to the problems of too long training time and falling into local extreme values when dealing with text classification. Therefore, the DBN is improved by introducing adaptive learning rate and additional momentum items, and is invested in text classification tasks: Propose a Deep Belief Network (LMDBN) based on an adaptive learning rate-additional momentum term. The algorithm can make the convergence of the network tend to the global minimum, and ensure that the convergence process is gentler and more stable, and at the same time accelerate the convergence process of the network. Experimental results show that the LMDBN network is better than the DBN in terms of classification accuracy and convergence time. Compared with several other traditional classification models, the LMDBN network also shows good classification performance.
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
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Geoffrey, E.: Hinton, Simon Osindero and Yee-Whye Teh: a fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
Junfei, Q., Gongming, W., **aoli, L.: Design and application of deep belief network based on adaptive learning rate. J. Autom. 43(08), 1339–1349 (2017). (in Chinese)
Gongming, W., QingShan, J., Junfei, Q.: A sparse deep belief network with efficient fuzzy learning framework. Neural Netw. Official J. Int. Neural Netw. Soc. 121, 430–440 (2020)
Yi, X., Beibei, L., Wei, S.: Research on improved deep belief network classification algorithm. Comput. Sci. Explor. 13(04), 596–607 (2019). (in Chinese)
Fischer, A., Igel, C.: An introduction to restricted boltzmann machines. In: Alvarez, L., Mejail, M., Gomez, L., Jacobo, J. (eds.) CIARP 2012. LNCS, vol. 7441, pp. 14–36. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33275-3_2
Li, L., Zhou, Z., Chen, D.: Offline handwritten Chinese character recognition based on the integration of DBN and CNN. J. Harbin Univ. Sci. Technol. 25(03), 137–143 (2020). (in Chinese)
Hinton, G.E.: A practical guide to training restricted Boltzmann machines. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 599–619. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-35289-8_32
Cai, L., Cai, X.: Application of DBN in Chinese text classification. Comput. Eng. Des. 39(09), 2974–2978+2991 (2018). (in Chinese)
Shi, J., Wang, D., Shang, F.: Research progress of stochastic gradient descent algorithm. J. Autom. 1–17[-04–03] (2021). (in Chinese)
Sun, Y.: Design of Doherty Power Amplifier Based on BP Algorithm Based on Adaptive Learning Rate Additional Momentum Term. East China Jiaotong University (2021). (in Chinese)
Acknowledgements
This work was supported by Industry Innovation Talent Team of Inner Mongolia Grassland Talent Engineering (2017), Science and Technology Projects of Inner Mongolia Autonomous Region (2020GG0190), Research Program of Science and Technology at Universities of Inner Mongolia Autonomous Region (NJZY20112), Program for Young Talents of Science and Technology in Universities of Inner Mongolia Autonomous Region (NJYT-19-B18), Natural Science Foundation of Inner Mongolia Autonomous Region of China (2019MS08036), Inner Mongolia University for Nationalities doctoral research start fund project (BS543).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Shi, Y., Jiang, J., Fan, X., Lian, J., Pei, Z., Jiang, M. (2022). An Improved DBN Method for Text Classification. In: Hung, J.C., Yen, N.Y., Chang, JW. (eds) Frontier Computing. FC 2021. Lecture Notes in Electrical Engineering, vol 827. Springer, Singapore. https://doi.org/10.1007/978-981-16-8052-6_110
Download citation
DOI: https://doi.org/10.1007/978-981-16-8052-6_110
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-8051-9
Online ISBN: 978-981-16-8052-6
eBook Packages: EngineeringEngineering (R0)