R
Roger Frigola
Researcher at University of Cambridge
Publications - 11
Citations - 480
Roger Frigola is an academic researcher from University of Cambridge. The author has contributed to research in topics: Gaussian process & Bayesian inference. The author has an hindex of 7, co-authored 11 publications receiving 425 citations.
Papers
More filters
Posted Content
Bayesian Inference and Learning in Gaussian Process State-Space Models with Particle MCMC
TL;DR: This work presents a fully Bayesian approach to inference and learning in nonlinear nonparametric state-space models and places a Gaussian process prior over the state transition dynamics, resulting in a flexible model able to capture complex dynamical phenomena.
Posted Content
Variational Gaussian Process State-Space Models
TL;DR: This work presents a procedure for efficient variational Bayesian learning of nonlinear state-space models based on sparse Gaussian processes and offers the possibility to straightforwardly trade off model capacity and computational cost whilst avoiding overfitting.
Proceedings Article
Variational Gaussian Process State-Space Models
TL;DR: In this article, a procedure for efficient variational Bayesian learning of nonlinear state-space models based on sparse Gaussian processes is presented, which offers the possibility to straightforwardly trade off model capacity and computational cost whilst avoiding overfitting.
Proceedings Article
Bayesian Inference and Learning in Gaussian Process State-Space Models with Particle MCMC
TL;DR: In this paper, a fully Bayesian approach to inference and learning in nonlinear nonparametric state-space models is presented, where a Gaussian process prior is placed over the state transition dynamics, resulting in a flexible model able to capture complex dynamical phenomena.
Proceedings ArticleDOI
Integrated pre-processing for Bayesian nonlinear system identification with Gaussian processes
TL;DR: A Bayesian model of the system's dynamics is obtained which is able to report its uncertainty in regions where the data is scarce and makes GP-FNARX a good candidate for applications in robotics and adaptive control.