In
Gaussian processes are a powerful, non-parametric tool that can be be used in supervised learning, namely in regression but also in classification problems. The main advantages of this method are the ability of GPs to provide uncertainty estimates and to learn the noise and smoothness parameters from training data. The aim of this short tutorial is to provide the basic theoretical aspects of Gaussian Processes, as well as a brief practical overview on implementation. The main motivation of this work was to develop a new approach to detect outliers on acoustic navigation algorithms for Autonomous Underwater Vehicles, capable of adjusting to different operation scenarios, since this is a major problem in the majority of Autonomous Underwater Vehicles. In the last part of the tutorial, a brief insight on this actual problem, and the solution proposed, that involves Gaussian Processes as a predictor, and some background subtraction techniques is described.
@inproceedings{meloGaussianProcessesRegression2012,
title = {Gaussian {{Processes}} for Regression : A Tutorial},
shorttitle = {Gaussian {{Processes}} for Regression},
abstract = {Gaussian processes are a powerful, non-parametric tool that can be be used in supervised learning, namely in regression but also in classification problems. The main advantages of this method are the ability of GPs to provide uncertainty estimates and to learn the noise and smoothness parameters from training data. The aim of this short tutorial is to provide the basic theoretical aspects of Gaussian Processes, as well as a brief practical overview on implementation. The main motivation of this work was to develop a new approach to detect outliers on acoustic navigation algorithms for Autonomous Underwater Vehicles, capable of adjusting to different operation scenarios, since this is a major problem in the majority of Autonomous Underwater Vehicles. In the last part of the tutorial, a brief insight on this actual problem, and the solution proposed, that involves Gaussian Processes as a predictor, and some background subtraction techniques is described.},
date = {2012},
keywords = {Acoustic cryptanalysis,Activation function,Algorithm,Approximation,Background subtraction,Effective method,Estimated,Expectation propagation,Gaussian process,Kalman filter,Kerrison Predictor,Normal Statistical Distribution,Subtraction Technique,Supervised learning},
author = {Melo, José},
file = {/home/dimitri/Nextcloud/Zotero/storage/2BMFEMFB/Melo - 2012 - Gaussian Processes for regression  a tutorial.pdf}
}