Parallel training of deep stacking networks

13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012

Volumn 3, Issue , 2012, Pages 2597-2600

  Deng, Li ^a   Hutchinson, Brian ^b   Yu, Dong ^a  

^a MICROSOFT RESEARCH   (United States)

^b UNIVERSITY OF WASHINGTON   (United States)

Author keywords

Deep stacking networks; Full batch training; Parallel and distributed computing; Phone classification

Indexed keywords

DEEP ARCHITECTURES; EXPERIMENTAL CONDITIONS; PARALLEL AND DISTRIBUTED COMPUTING; PARALLEL IMPLEMENTATIONS; PARALLEL LEARNING; PARALLEL TRAINING; PHONE CLASSIFICATIONS; TRAINING ALGORITHMS;

ARCHITECTURAL DESIGN;

TELEPHONE SETS;

EID: 84878540767     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (17)

1. A. Beck and M. Teboulle. "Gradient-based methods with application to signal recovery problems," In D. Palomar and Y. Eldar, editors, Convex Optimization in Signal Processing and Communications. Cambridge, University Press, 2010.
2. Y. Bengio. "Learning deep architectures for AI," Foundations and Trends in Machine Learning, vol. 2, no. 1, pp. 1-127, 2009.
3. B. Hutchinson, L. Deng, and D. Yu, "A deep architecture with bilinear modeling of hidden representations: Applications to phonetic recognition," Proc. ICASSP 2012.
4. G.E. Dahl, D. Yu, L. Deng, and A. Acero, "Context-dependent pretrained deep neural networks for large vocabulary speech recognition," IEEE Trans. Audio, Speech, and Lang. Proc. Jan. 2012.
5. L. Deng and D. Yu. "Deep Convex Network: A scalable architecture for deep learning," In Proc. Interspeech, 2011.
6. L. Deng, D. Yu, and J. Platt. "Scalable stacking and learning for building deep architectures," In Proc. ICASSP, 2012.
7. L. Deng, M. Seltzer, D. Yu, A. Acero, A. Mohamed, and G. Hinton. "Binary coding of speech spectrograms using a deep auto-encoder," In Proc. Interspeech, September 2010.
8. D. Liu and J. Nocedal. "On the limited memory (BFGS) method for large scale optimization," J. Mathematical Programming, Vol. 45, No.3, 503-528, 1989.
9. J. Godfrey and E. Holliman, "Switchboard-1 Release 2," Linguistic Data Consortium, Philadelphia, 1997.
10. G. Hinton and R. Salakhutdinov. "Reducing the dimensionality of data with neural networks," Science, vol. 313, 504-507, 2006.
11. A. Mohamed, G. E. Dahl, and G. E. Hinton, "Acoustic modeling using deep belief networks," IEEE Trans. on Audio, Speech, and Lang. Proc. Jan. 2012.
12. D. B. Paul and J. M. Baker, "The design for the Wall Street Journal based CSR corpus," in Proc. Int. Conf. Spoken Lang. Processing, 1992.
13. S. Renals, N. Morgan, H. Bourlard, M. Cohen, and H. Franco. "Connectionist Probability Estimators in HMM Speech Recognition," IEEE Trans. Speech and Audio Proc., January 1994.
14. R. Salakhutdinov and G. Hinton. Deep Boltzmann machines. In Proc. AISTATS, 2009.
15. G. Tur, L. Deng, D. Hakkani-Tür, and X. He. "Towards deep understanding: Deep convex networks for semantic utterance classification," In Proc. ICASSP, 2012.
16. D. Wolpert. "Stacked generalization," In Neural Networks, vol. 5(2), pp 241-259, 1992.
17. D. Yu, and L. Deng. "Accelerated parallelizable neural networks learning algorithms for speech recognition," In Proc. Interspeech, 2011.