论文信息 - Learning nonlinear dynamic models

Learning nonlinear dynamic models

We present a novel approach for learning nonlinear dynamic models, which leads to a new set of tools capable of solving problems that are otherwise difficult. We provide theory showing this new approach is consistent for models with long range structure, and apply the approach to motion capture and high-dimensional video data, yielding results superior to standard alternatives.

[1] John Langford,et al. Approximately Optimal Approximate Reinforcement Learning , 2002, ICML.

[2] Geoffrey E. Hinton,et al. Modeling Human Motion Using Binary Latent Variables , 2006, NIPS.

[3] Jun S. Liu,et al. Mixture Kalman ®lters , 2000 .

[4] N. Gordon,et al. Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[5] Jun S. Liu,et al. Mixture Kalman filters , 2000 .

[6] Kristine L. Bell,et al. A Tutorial on Particle Filters for Online Nonlinear/NonGaussian Bayesian Tracking , 2007 .

[7] Neil J. Gordon,et al. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[8] John Langford,et al. Search-based structured prediction , 2009, Machine Learning.

[9] Aaron F. Bobick,et al. Parametric Hidden Markov Models for Gesture Recognition , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[10] Sham M. Kakade,et al. A spectral algorithm for learning Hidden Markov Models , 2008, J. Comput. Syst. Sci..

[11] Michael A. West,et al. Bayesian forecasting and dynamic models (2nd ed.) , 1997 .

[12] Zoubin Ghahramani,et al. Learning Nonlinear Dynamical Systems Using an EM Algorithm , 1998, NIPS.