Description Usage Arguments Details Value Author(s) References
This function delivers two applications: 1. Training : When no test data are given, the function returns minus the log likelihood and its partial derivatives with respect to the hyperparameters. Training method is to fit the hyperparameters.
2.Prediction: If test data are given, then marginal Gaussian predictions are computed, and function returns mean and variance describing the Gaussian predictions. In cases where the covariance function has noise contributions, the variance returned in S2 variable is for noisy test targets. To have variance of the noisefree latent function, the noise variance should be substracted .
1 
logtheta 

covfunc.gpr 

x 

y 

xstar 

partial.derivatives 
Logical value that when it is TRUE and the test data is given gpr executes prediction process. 
There are only covSum
, covNoise
and covSEiso
covariance functions available in this package to be used with gaussion process. More ever this is an open source script with line by line description so that you can learn the code and write your own covariance functions to call gpr on them. If you like to contribute and add your own functions to this package please contact the package maintainer. Please refere to references to get info about the other consistent covariance functions.
When partial.derivatives
is FALSE returns a list containing minus the log likelihood and its vector of partial derivatives .
When partial.derivatives
is TRUE returns a list that consists of two objects. The first is a mean vector which same number of rows of x
and y
and the second object variance vector that has same number of rows of x
and y
. They describe the result Gaussian prediction.
Afshin Sadeghi
1. Carl Edward Rasmussen and Christopher K. I. Williams.Gaussian Processes for Machine Learning. MIT Press, 2006. ISBN 026218253X. 2. Carl Edward Rasmussen & Hannes Nickisch. gpml(GAUSSIAN PROCESS REGRESSION AND CLASSIFICATION Toolbox) Matlab Library.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.