Analytic moment-based Gaussian process filtering

By Marc Peter Deisenroth, Marco F. Huber, Uwe D. Hanebeck. 2009

162 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistical and Nonlinear Physics

Citations in the corpus

Predictive-State Decoders: Encoding the Future into Recurrent Networks (2017, background): “A classical supervised machine learning approach for learning internal models involves choosing an explicit parametrization for the internal states and assuming ground-truth access to these states and observations at training time [17, 29, 33, 37].”
Monte Carlo Filtering Using Kernel Embedding of Distributions (2014, methodology): “For this setting, nonparametric filters using kernel embeddings (Song et al. 2009; Fukumizu, Song, and Gretton 2011) or Gaussian processes (Ko and Fox 2009; Deisenroth, Huber, and Hanebeck 2009) were proposed.”
The Nonparametric Kernel Bayes Smoother (2016, methodology): “The same assumption is made in the nKB-filter [10] and the GP-based filter/smoother [17, 6, 7].”
Learning GP-BayesFilters via Gaussian process latent variable models (2009, methodology): “More recently, the GP-BayesFilter framework has been extended to also include assumed density filters (ADF) (Deisenroth et al. 2009).”
Expectation Propagation in Gaussian Process Dynamical Systems (2012, methodology): “However, the mean and covariance of a Gaussian approximation Z̃M to ZM can be computed analytically: either using exact moment matching [14, 3], or approximately by expected linearization of the posterior GP [8]; details are given in [4].”
Cautious Model Predictive Control Using Gaussian Process Regression (2017, methodology): “For the case of the squared exponential kernel, this has been shown to offer universal function approximation [14].”