Abstract
The gradient-descent learning of deep neural networks is subject to local minima, and good initialization may depend on the tasks. In contrast, for document classification tasks, latent Dirichlet allocation (LDA) was quite successful in extracting topic representations, but its performance was limited by its shallow architecture. In this study, LDA was adopted for efficient layer-by-layer pre-training of deep neural networks for a document classification task. Two-layer feedforward networks were added at the end of the process, and trained using a supervised learning algorithm. With 10 different random initializations, the LDA-based initialization generated a much lower mean and standard deviation for false recognition rates than other state-of-the-art initialization methods. This might demonstrate that the multi-layer expansion of probabilistic generative LDA model is capable of extracting efficient hierarchical topic representations for document classification.
This work was supported by the ICT R&D program of MSIP/IITP, Republic of Korea (R0126-15-1117, Core technology development of spontaneous speech dialogue processing for the language learning).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)
Bengio, Y.: Learning deep architectures for AI. Found. Trends Mach. Learn. 2, 1–127 (2007)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18, 1527–1554 (2006)
Charalampous, K., Kostavelis, I., Amanatiadis, A., Gasteratos, A.: Sparse deep-learning algorithm for recognition and categorisation. Electron. Lett. 48, 1265–1266 (2012)
Erhan, D., Bengio, Y., Courville, A., Manzagol, P.-A., Vincent, P., Bengio, S.: Why does unsupervised pre-training help deep learning? J. Mach. Learn. Res. 11, 625–660 (2010)
Sutskever, I., Martens, J., Dahl, G., Hinton, G.: On the importance of initialization and momentum in deep learning. In: 30th International Conference on Machine Learning, Atlanta, USA, pp. 1139–1147, June 2013
Haidar, M.A., O’Shaughnessy, D.: Unsupervised language model adaptation using LDA-based mixture models and latent semantic marginals. Comput. Speech Lang. 29, 20–31 (2015)
Song, H.A., Kim, B.K., Xuan, T.L., Lee, S.Y.: Hierachical feature extraction by multi-layer non-negative matrix factorization network for classification task. Neurocomputing 165, 63–74 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Jeon, HB., Lee, SY. (2016). Initializing Deep Learning Based on Latent Dirichlet Allocation for Document Classification. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds) Neural Information Processing. ICONIP 2016. Lecture Notes in Computer Science(), vol 9949. Springer, Cham. https://doi.org/10.1007/978-3-319-46675-0_70
Download citation
DOI: https://doi.org/10.1007/978-3-319-46675-0_70
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-46674-3
Online ISBN: 978-3-319-46675-0
eBook Packages: Computer ScienceComputer Science (R0)