wolffd@0: wolffd@0: wolffd@0: wolffd@0: Netlab Reference Manual demgpard wolffd@0: wolffd@0: wolffd@0: wolffd@0:

demgpard wolffd@0:

wolffd@0:

wolffd@0: Purpose wolffd@0:

wolffd@0: Demonstrate ARD using a Gaussian Process. wolffd@0: wolffd@0:

wolffd@0: Synopsis wolffd@0:

wolffd@0:

wolffd@0: demgpare

wolffd@0: wolffd@0: wolffd@0:

wolffd@0: Description wolffd@0:

wolffd@0: The data consists of three input variables x1, x2 and wolffd@0: x3, and one target variable wolffd@0: t. The wolffd@0: target data is generated by computing sin(2*pi*x1) and adding Gaussian wolffd@0: noise, x2 is a copy of x1 with a higher level of added wolffd@0: noise, and x3 is sampled randomly from a Gaussian distribution. wolffd@0: A Gaussian Process, is wolffd@0: trained by optimising the hyperparameters wolffd@0: using the scaled conjugate gradient algorithm. The final values of the wolffd@0: hyperparameters show that the model successfully identifies the importance wolffd@0: of each input. wolffd@0: wolffd@0:

wolffd@0: See Also wolffd@0:

wolffd@0: demgp, gp, gperr, gpfwd, gpgrad, gpinit, scg

wolffd@0: Pages: wolffd@0: Index wolffd@0:

wolffd@0: