Herding dynamic weights for partially observed random field models

Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009

Volumn , Issue , 2009, Pages 599-606

  Welling, Max ^a  

^a Ringgold Standard Institution Informatics   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DYNAMICAL SYSTEMS;

COMPLEX DYNAMICS; DYNAMIC WEIGHT; EXPONENTIATIONS; OPTIMAL PARAMETER; RANDOM FIELD MODEL; STATE VECTOR;

ARTIFICIAL INTELLIGENCE;

EID: 79959651429     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. J. Besag. Efficiency of pseudo-likelihood estimation for simple Gaussian fields. Biometrika, 64:616-618, 1977. (Pubitemid 8238543)
2. A. Goetz. Dynamics of piecewise isometries. Illinois Journal of Math, 44:3:465-478, 2000.
3. G.E. Hinton. Training products of experts by minimizing contrastive divergence. Neural Computation, 14:1771-1800, 2002.
4. A. Hyvarinen. Estimation of non-normalized statistical models using score matching. Journal of Machine Learning Research, 6:695-709, 2005.
5. W. Maass and A. M. Zador. Dynamic stochastic synapses as computational units. In Advances in Neural Information Processing Systems, pages 903-917. MIT Press, 1998.
6. I. Murray and Z. Ghahramani. Bayesian learning in undirected graphical models: approximate MCMC algorithms. In Proceedings of the 14th Annual Conference on Uncertainty in AI, pages 392-399, 2004.
7. R.M. Neal. Connectionist learning of belief networks. Articial Intelligence, 56:71-113, 1992.
8. T. Tieleman. Training restricted boltzmann machines using approximations to the likelihood gradient. In Proceedings of the International Conference on Machine Learning, volume 25, pages 1064-1071, 2008.
9. T. Tieleman and G.E. Hinton. Using Fast Weights to Improve Persistent Contrastive Divergence. In Proceedings of the International Conference on Machine Learning, volume 26, 2009.
10. M. Welling. Herding dynamical weights to learn. In Proceedings of the 21st International Conference on Machine Learning, Montreal, Quebec, CAN, 2009.
11. M. Welling and S. Parise. Bayesian random fields: The Bethe-Laplace approximation. In Proc. of the Conf. on Uncertainty in Artificial Intelligence, pages 512-519, 2006.
12. M. Welling, R. Zemel, and G.E. Hinton. Self-supervised boosting. In Neural Information Processing Systems, volume 15, Vancouver, Canada, 2002.
13. L. Younes. Parametric inference for imperfectly observed gibbsian fields. Probability Theory and Related Fields, 82:625-645, 1989.
14. A.L. Yuille. The convergence of contrastive divergences. In Advances in Neural Information Processing Systems, volume 17, pages 1593-1600, 2004.
15. S.C. Zhu and X.W. Liu. Learning in Gibbsian fields: How accurate and how fast can it be? IEEE Trans. on Pattern Analysis and Machine Intelligence, 24(7):1001-1006, 2002. (Pubitemid 34835474)