Kriging - Expensive Expensivesurrogates

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
xpensive surrogates Expensive surrogates In linear regression, the process of fitting involves solving a set of linear equations. This is because the optimization problems of minimizing rms is solved by this system. With other loss functions or other surrogates we often ave to solve an expensive optimization problem. have to solve an expensive optimization problem. This is why polynomial response surfaces were almost exclusively used until the last 20 years. For radial basis neural networks we may undertake to find the best spread by minimizing cross correlation RESS) error (PRESS) error.
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Universal Kriging ˆ () xx x v N i y Z   Linear trend model 2 p ) () ) s v N Z s 1 ii i Systematic departure Named after a South African y Sampling data points Linear Trend     1 exp , , xs θ i i C ZZ  mining engineer D. G. Krige Assumption: Systematic Model departures Z( x ) are correlated Gaussian correlation function ( most popular
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 06/06/2011 for the course EAS 4240 taught by Professor Peterifju during the Spring '08 term at University of Florida.

Page1 / 5

Kriging - Expensive Expensivesurrogates

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online