Learning deep dynamical models from image pixels

IFAC-PapersOnLine

Volumn 48, Issue 28, 2015, Pages 1059-1064

  Wahlström, Niklas ^a   Schön, Thomas B ^b   Deisenroth, Marc Peter ^c  

^a LINKÖPING UNIVERSITY   (Sweden)

^b UPPSALA UNIVERSITY   (Sweden)

^c IMPERIAL COLLEGE LONDON   (United Kingdom)

Author keywords

auto encoder; Deep neural networks; low dimensional embedding; nonlinear systems; system identification

Indexed keywords

DEEP LEARNING; DEEP NEURAL NETWORKS; DYNAMICAL SYSTEMS; EMBEDDINGS; IDENTIFICATION (CONTROL SYSTEMS); LINEAR SYSTEMS; MAPPING; NONLINEAR SYSTEMS; PIXELS; PREDICTIVE ANALYTICS; RELIGIOUS BUILDINGS; SIGNAL ENCODING; SYSTEM THEORY;

AUTO ENCODERS; HIGH-DIMENSIONAL; LOW DIMENSIONAL EMBEDDING; LOW-DIMENSIONAL SPACES; NON-LINEAR SYSTEM IDENTIFICATION; PIXEL INFORMATION; PREDICTIVE MODELS; TRANSITION MODEL;

LEARNING SYSTEMS;

EID: 84988663071     PISSN: None     EISSN: 24058963     Source Type: Conference Proceeding    
DOI: 10.1016/j.ifacol.2015.12.271     Document Type: Conference Paper

References (18)

1. Bourlard, H., Kamp, Y., Auto-association by multilayer perceptrons and singular value decomposition. Biological cybernetics 59:4-5 (1988), 291–294.
2. Deisenroth, M.P., Fox, D., Rasmussen, C.E., Gaussian processes for data-efficient learning in robotics and control. IEEE Transaction on Pattern Analysis and Machine Intelligence 37:2 (2015), 408–423.
3. Doretto, G., Chiuso, A., Wu, Y.N., Soatto, S., Dynamic textures. International Journal of Computer Vision 51:2 (2003), 91–109.
4. Ghahramani, Z. (1998). Learning dynamic bayesian networks. In C. Giles and M. Gori (eds.), Adaptive Processing of Sequences and Data Structures, volume 1387 of Lecture Notes in Computer Science, 168-197. Springer.
5. Gibson, S., Ninness, B., Robust maximumlikelihood estimation of multivariable dynamic systems. Automatica 41:10 (2005), 1667–1682.
6. Hinton, N., Salakhutdinov, R., Reducing the dimensionality of data with neural networks. Science 313 (2006), 504–507.
7. Kantas, N., Doucet, A., Singh, S.S., Maciejowski, J., and Chopin, N. (2015). On particle methods for parameter estimation in state-space models. Statistical Science. Accepted for publication.
8. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., Gradient-based learning applied to document recognition. Proceedings of the IEEE 86:11 (1998), 2278–2324.
9. Ljung, L. (1999). System identification, Theory for the user. System sciences series. Prentice Hall, Upper Saddle River, NJ, USA, second edition.
10. Ljung, L., Perspectives on system identification. Annual Reviews in Control 34:1 (2010), 1–12.
11. Nocedal, J. and Wright, S.J. (2006). Numerical Optimization. Springer Series in Operations Research. New York, USA, 2 edition.
12. Schneider, J.G., Exploiting model uncertainty estimates for safe dynamic control learning. In NIPS, 1997.
13. Schön, T.B., Wills, A., Ninness, B., System identification of nonlinear state-space models. Automatica 47:1 (2011), 39–49.
14. Shumway, R.H., Stoffer, D.S., An approach to time series smoothing and forecasting using the EM algorithm. Journal of Time Series Analysis 3:4 (1982), 253–264.
15. Sjöberg, J., Zhang, Q., Ljung, L., Benveniste, A., Delyon, B., Glorennec, P.Y., Hjalmarsson, H., Juditsky, A., Nonlinear black-box modeling in system identification: a unified overview. Automatica 31:12 (1995), 1691–1724.
16. Van Overschee, P., De Moor, B., Subspace identification for linear systems - theory, implementation, applications., 1996, Kluwer Academic Publishers.
17. Vincent, P., Larochelle, H., Bengio, Y., and Manzagol, P.A. (2008). Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th International Conference on Machine Learning (ICML). Helsinki, Finland.
18. Wahlström, N., Schön, T.B., and Deisenroth, M.P. (2015). From pixels to torques: Policy learning with deep dynamical models. Preprint, arXiv:1502.02251.