Factored conditional restricted Boltzmann machines for modeling motion style

Proceedings of the 26th International Conference On Machine Learning, ICML 2009

Volumn , Issue , 2009, Pages 1025-1032

  Taylor, Graham W ^a   Hinton, Geoffrey E ^a  

^a UNIVERSITY OF TORONTO   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

COMPACT MODEL; COMPUTATIONAL PROPERTIES; DYNAMIC STATE; EFFECTIVE INTERACTIONS; EXACT INFERENCE; HIDDEN STATE; HUMAN MOTIONS; MOTION STYLES; MULTIPLICATIVE MODEL; NEW MODEL; RESTRICTED BOLTZMANN MACHINE;

TIME SERIES;

ROBOT LEARNING;

EID: 71149118574     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (20)

1. Brand, M., & Hertzmann, A. (2000). Style machines. Proc. Conf. on Comp. Graph. and Int. Techn. (pp. 183-192).
2. Carreira-Perpinan, M., & Hinton, G. (2005). On contrastive divergence learning. Proc. Int. Conf. on Artif. Intel. and Stat. (pp. 59-66).
3. Freund, Y., & Haussler, D. (1992). Unsupervised learning of distributions of binary vectors using 2-layer networks. Adv. in Neural Inf. Proc. Sys. (pp. 912-919).
4. Hinton, G. (2002). Training products of experts by minimizing contrastive divergence. Neural Comput, 14, 1771-1800.
5. Hinton, G., Osindero, S., & Teh, Y. (2006). A fast learning algorithm for deep belief nets. Neural Comput, 18, 1527-1554.
6. Hinton, G., & Salakhutdinov, R. (2006). Reducing the dimensionality of data with neural networks. Science, 313, 504-507.
7. Hsu, E., Pulli, K., & Popović, J. (2005). Style translation for human motion. Proc. Conf. on Comp. Graph. and Int. Techn. (pp. 1082-1089).
8. Lawrence, N. (2004). Gaussian process latent variable models for visualisation of high dimensional data. Adv. in Neural Inf. Proc. Sys. (pp. 329-326).
9. Lee, H., Ekanadham, C., & Ng., A. (2008). Sparse deep belief net model for visual area V2. Adv. in Neural Inf. Proc. Sys. (pp. 873-880).
10. Memisevic, R. (2008). Non-linear latent factor models for revealing structure in high-dimensional data. Doctoral dissertation, University of Toronto.
11. Memisevic, R., & Hinton, G. (2007). Unsupervised learning of image transformations. Proc. IEEE Comp. Soc. Conf. on Comp. Vis. and Pat. Rec.
12. Osindero, S., & Hinton, G. (2008). Modeling image patches with a directed hierarchy of Markov random fields. Adv. in Neural Inf. Proc. Sys. (pp. 1121-1128).
13. Salakhutdinov, R., Mnih, A., & Hinton, G. (2007). Restricted Boltzmann machines for collaborative filtering-filtering. Proc. Int. Conf. on Mach. Learn. (pp. 791-798).
14. Salakhutdinov, R., & Murray, I. (2008). On the quantitative analysis of deep belief networks. Proc. Int. Conf. on Mach. Learn. (pp. 872-879).
15. Smolensky, P. (1986). Information processing in dynamical systems: Foundations of harmony theory. In D. E. Rumelhart, J. L. McClelland et al. (Eds.), Parallel distributed processing: Volume 1: Foundations, 194-281. Cambridge: MIT Press.
16. Taylor, G., Hinton, G., & Roweis, S. (2007). Modeling human motion using binary latent variables. Adv. in Neural Inf. Proc. Sys. (pp. 1345-1352).
17. Tieleman, T. (2008). Training restricted Boltzmann machines using approximations to the likelihood gradient. Proc. Int. Conf. on Mach. Learn. (pp. 1064-1071).
18. Torresani, L., Hackney, P., & Bregler, C. (2007). Learning motion style synthesis from perceptual observations. Adv. in Neural Inf. Proc. Sys. (pp. 1393-1400).
19. Wang, J., Fleet, D., & Hertzmann, A. (2007). Multifac-tor gaussian process models for style-content separation. Proc. Int. Conf. on Mach. Learn. (pp. 975-982).
20. Welling, M., Rosen-Zvi, M., & Hinton, G. (2005). Exponential family harmoniums with an application to information retrieval. Adv. in Neural Inf. Proc. Sys. (pp. 1481-1488).