State-Space Inference and Learning with Gaussian Processes
R.D. Turner, Marc Peter Deisenroth, Carl Edward Rasmussen · MPG.PuRe (Max Planck Society) · 2010
State-space inference and learning with Gaussian processes (GPs) is an unsolved problem.We propose a new, general methodology for inference and learning in nonlinear state-space models that are described probabilistically by non-parametric GP models.We apply the expectation maximization algorithm to iterate between inference in the latent state-space and learning the parameters of the underlying GP dynamics model.