A deep and tractable density estimator

31st International Conference on Machine Learning, ICML 2014

Volumn 1, Issue , 2014, Pages 719-727

  Uria, Benigno ^a   Murray, Iain ^a   Larochelle, Hugo ^b  

^a UNIVERSITY OF EDINBURGH   (United Kingdom)

^b UNIVERSITÉ DE SHERBROOKE   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE;

APPROXIMATE INFERENCE; AUTO-REGRESSIVE; DATA DIMENSIONS; DENSITY ESTIMATION; DENSITY ESTIMATOR; MULTIDIMENSIONAL DATA; STATE OF THE ART; TRAINING PROCEDURES;

LEARNING SYSTEMS;

EID: 84919786489     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. Bache, K. and Lichman, M. UCI machine learning repository, 2013. http://archive.ics.uci.edu/ml.
2. Bengio, Y. Learning deep architectures for AL Foundations and trends in Machine Learning, 2(1):1-127, 2009.
3. Bengio, Y. and Bengio, S. Modeling high-dimensional discrete data with multi-layer neural networks. In Advances in Neural Information Processing Systems 12 (NIPS 1999), pp. 400-406. MIT Press, 2000.
4. Bishop, C. M. Mixture density networks. Technical report, Neural Computing Research Group, Aston University, 1994.
5. Bishop, C. M. Pattern recognition and machine learning. Springer-Verlag, New York, 2006. ISBN 0387310738.
6. Frey, B. J. Graphical models for machine learning and digital communication. MIT Press, 1998.
7. Goodfellow, I., Mirza, M., Courville, A., and Bengio, Y. Multi-prediction deep Boltzmann machines. In Advances in Neural Information Processing Systems 26, pp. 548-556. 2013.
8. Gregor, K. and LeCun, Y. Learning representations by max imizing compression. Technical report, arXiv:1108.1169, 2011.
9. Larochelle, H. and Murray, I. The Neural Autoregressive Distribution Estimator. In Proceedings of the 14th Inter national Conference on Artificial Intelligence and Statistics (AISTATS 2011), volume 15, pp. 29-37, Ft. Laud erdale, USA, 2011. JMLR W&CP.
10. Murray, I. and Salakhutdinov, R. Evaluating probabili ties under high-dimensional latent variable models. In Advances in Neural Information Processing Systems 21 (NIPS 2008), pp. 1137-1144, 2009.
11. Nair, V. and Hinton, G. E. Rectified linear units improve re stricted Boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 807-814, 2010.
12. Ormoneit, D. and Tresp, V. Improved Gaussian mixture den sity estimates using Bayesian penalty terms and network averaging. In Advances in Neural Information Processing Systems 8 (NIPS 1995), pp. 542-548. MIT Press, 1996.
13. Salakhutdinov, R. and Murray, I. On the quantitative analy sis of deep belief networks. In Proceedings of the 25th International Conference on Machine Learning (ICML 2008), volume 25, pp. 872-879, 2008.
14. Smyth, P. and Wolpert, D. Linearly combining density estimators via stacking. Machine Learning, 36(l-2):59-83, 1999.
15. Sutskever, I. Training recurrent neural networks. PhD thesis, University of Toronto, 2013.
16. Uria, B., Murray, I., and Larochelle, H. RNADE: The real-valued neural autoregressive density-estimator. In Advances in Neural Information Processing Systems 26 (NIPS 26), 2013. To appear. arXiv: 1306.0186.
17. Vincent, P., Larochelle, H., Bengio, Y., and Manzagol, P. A. Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th International Conference on Machine Learning (ICML 2008), pp. 1096-1103, Helsinki, Finland, 2008. ACM.
18. Zoran, D. and Weiss, Y. Natural images, Gaussian mixtures and dead leaves. In Advances in Neural Information Pro cessing Systems 25 (NIPS 2012), pp. 1745-1753, 2012.