Abstract
In this chapter, we introduce several advanced deep neural network (DNN) model initialization or pretraining techniques. These techniques have played important roles in the early days of deep learning research and continue to be useful under many conditions. We focus our presentation of pretraining DNNs on the following topics: the restricted Boltzmann machine (RBM), which by itself is an interesting generative model, the deep belief network (DBN), the denoising autoencoder, and the discriminative pretraining.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: Proceedings of the Neural Information Processing Systems (NIPS), pp. 153–160 (2006)
Bottou, L.: Online learning and stochastic approximations. On-line Learn. Neural Netw. 17, 9 (1998)
Coates, A., Ng, A.Y., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 215–223 (2011)
Dahl, G.E., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio, Speech Lang. Process. 20(1), 30–42 (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. (JMLR) 11, 625–660 (2010)
Erhan, D., Manzagol, P.A., Bengio, Y., Bengio, S., Vincent, P.: The difficulty of training deep architectures and the effect of unsupervised pre-training. In: Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 153–160 (2009)
Hinton, G.: A practical guide to training restricted Boltzmann machines. Technical Report UTML TR 2010-003, University of Toronto (2010)
Hinton, G., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18, 1527–1554 (2006)
Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14(8), 1771–1800 (2002)
Hinton, G.E., Dayan, P., Frey, B.J., Neal, R.M.: The wake-sleep algorithm for unsupervised neural networks. SCIENCE-NEW YORK THEN WASHINGTON- pp. 1158–1158 (1995)
Hinton, G.E., Salakhutdinov, R.: Replicated softmax: an undirected topic model. In: Proceedings of the Neural Information Processing Systems (NIPS), pp. 1607–1614 (2009)
Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012)
Larochelle, H., Bengio, Y.: Classification using discriminative restricted Boltzmann machines. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 536–543 (2008)
Ling, Z.H., Deng, L., Yu, D.: Modeling spectral envelopes using restricted Boltzmann machines and deep belief networks for statistical parametric speech synthesis. IEEE Trans. Audio, Speech Lang. Process. 21(10), 2129–2139 (2013)
Sainath, T., Kingsbury, B., Ramabhadran, B.: Improving training time of deep belief networks through hybrid pre-training and larger batch sizes. In: Proceedings of the Neural Information Processing Systems (NIPS) Workshop on Log-linear Models (2012)
Salakhutdinov, R., Mnih, A., Hinton, G.: Restricted boltzmann machines for collaborative filtering. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 791–798 (2007)
Saul, L.K., Jaakkola, T., Jordan, M.I.: Mean field theory for sigmoid belief networks. J. Artif. Intell. Res. (JAIR) 4, 61–76 (1996)
Seide, F., Li, G., Chen, X., Yu, D.: Feature engineering in context-dependent deep neural networks for conversational speech transcription. In: Proceedings of the IEEE Workshop on Automfatic Speech Recognition and Understanding (ASRU), pp. 24–29 (2011)
Seide, F., Li, G., Yu, D.: Conversational speech transcription using context-dependent deep neural networks. In: Proceedings of the Annual Conference of International Speech Communication Association (INTERSPEECH), pp. 437–440 (2011)
Smolensky, P.: Information processing in dynamical systems: foundations of harmony theory. Department of Computer Science, University of Colorado, Boulder (1986)
Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 1096–1103 (2008)
Yu, D., Deng, L., Dahl, G.: Roles of pre-training and fine-tuning in context-dependent DBN-HMMs for real-world speech recognition. In: Proceedings of the Neural Information Processing Systems (NIPS) Workshop on Deep Learning and Unsupervised Feature Learning (2010)
Zhang, S., Bao, Y., Zhou, P., Jiang, H., Li-Rong, D.: Improving deep neural networks for LVCSR using dropout and shrinking structure. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6899–6903 (2014)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2015 Springer-Verlag London
About this chapter
Cite this chapter
Yu, D., Deng, L. (2015). Advanced Model Initialization Techniques. In: Automatic Speech Recognition. Signals and Communication Technology. Springer, London. https://doi.org/10.1007/978-1-4471-5779-3_5
Download citation
DOI: https://doi.org/10.1007/978-1-4471-5779-3_5
Published:
Publisher Name: Springer, London
Print ISBN: 978-1-4471-5778-6
Online ISBN: 978-1-4471-5779-3
eBook Packages: EngineeringEngineering (R0)