JGPR: a computationally efficient multi-target Gaussian process regression algorithmMachine learningGaussian process regressionMulti-task learningMulti-target regressionMachine Learning - Multi-target regression algorithms are designed to predict multiple outputs at the same time, and allow us to take all ...
A Heteroscedastic Gaussian Process Regression Algorithm (HGPR) implementation is based on the paper "Most Likely Heteroscedastic Gaussian Process Regression" by Kristian Kersting, Christian Plagemann, Patrick Pfaff and Wolfram Burgard.Unlike the homoscedastic algorithm, HGPR fits both target function and ...
Utilising this adaptive strategy, the Gaussian process based stochastic model predictive control (GP㏒MPC) algorithm is designed by applying the adaptive tightened constraints in all prediction horizons. To reduce the computation load, the one﹕tep GP㏒MPC algorithm is further developed by imposing the...
this method enhances the stability of the Gaussian process regression model by using the Bagging algorithm. In addition, the basis model in the Bagging framework is model-free. The simulation data analysis shows that the proposed model has smaller mean errors, relative errors and absolute errors re...
A new class of parameter estimation algorithms is introduced for Gaussian process regression (GPR) models. It is shown that the integration of the GPR model with probability distance measures of (i) the integrated square error and (ii) Kullback–Leibler (K–L) divergence are analytically ...
3.1Gaussian process regression The objective of GPR is to estimate a functionfin an online manner with low complexity. A Gaussian process (GP) is defined as a probability distribution over some variables, where any finite subset of these variables forms a joint Gaussian distribution [19]. This ...
Keywords:Gaussianprocess;hyper-parametersoptimization;memeticalgorithm;regressionmodel lIntr0ducti0n Beinganewkernelmethoddevelopedonthebasis ofstatisticallearningandBayesiantheorem.Gaussian process(GP)[1]iswelladaptabletoprocessingsuch complexproblemsasnon—linearity,smal1samplesize. ...
Step-wise additive GP regression algorithm The space of all models is large and thus an exhaustive search for the best model over the whole model space would be too slow in practice. Two commonly used model (or feature) selection methods include forward and backward search techniques. Starting ...
Then, local GPR models are built for each of the LDs and further integrated as finite mixture Gaussian process regression (FMGPR) models through FMM. Next, a Genetic Algorithm (GA) based ensemble pruning strategy is used to select the highly influential FMGPR models. When an estimation is ...
The proposed method integrates an appropriate kernel, benchmarked against the radiation transport code MCNP6, into the Gaussian Process Regression technique. The suitability of the proposed technique is demonstrated through its application to data collected from a bespoke robotic system used to conduct a...