Joint training of deep Boltzmann machines for classification

1st International Conference on Learning Representations, ICLR 2013 - Workshop Track Proceedings

Volumn , Issue , 2013, Pages

  Goodfellow, Ian J ^a   Courville, Aaron ^a   Bengio, Yoshua ^a  

^a UNIVERSITÉ DE MONTRÉAL   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATE INFERENCE; CLASSIFICATION TASKS; DEEP BOLTZMANN MACHINES; GENERATIVE MODEL; PSEUDO-LIKELIHOOD; RECURRENT NETWORKS; TRAINING PROCEDURES; VARIATIONAL APPROXIMATION;

RECURRENT NEURAL NETWORKS;

EID: 85083952643     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. Arnold, L. and Ollivier, Y. (2012). Layer-wise learning of deep generative models. Technical report, arXiv:1212.1524.
2. Goodfellow, I. J., Courville, A., and Bengio, Y. (2013). Scaling up spike-and-slab models for unsupervised feature learning. IEEE, special issue on deep learning. (To appear).
3. Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. (2012). Improving neural networks by preventing co-adaptation of feature detectors. Technical report, arXiv:1207.0580.
4. Le Roux, N. and Bengio, Y. (2008). Representational power of restricted Boltzmann machines and deep belief networks. Neural Computation, 20(6), 1631–1649.
5. Montavon, G. and Müller, K.-R. (2012). Learning feature hierarchies with cented deep Boltzmann machines. CoRR, abs/1203.4416.
6. Neal, R. M. (2001). Annealed importance sampling. Statistics and Computing, 11(2), 125–139.
7. Salakhutdinov, R. and Hinton, G. (2009). Deep Boltzmann machines. In Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS 2009), volume 8.
8. Stoyanov, V., Ropson, A., and Eisner, J. (2011). Empirical risk minimization of graphical model parameters given approximate inference, decoding, and model structure. In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS), volume 15 of JMLR Workshop and Conference Proceedings, pages 725–733, Fort Lauderdale. Supplementary material (4 pages) also available.
9. Tieleman, T. (2008). Training restricted Boltzmann machines using approximations to the likelihood gradient. In W. W. Cohen, A. McCallum, and S. T. Roweis, editors, ICML 2008, pages 1064–1071. ACM.
10. Younes, L. (1999). On the convergence of Markovian stochastic algorithms with rapidly decreasing ergodicity rates. Stochastics and Stochastic Reports, 65(3), 177–228.