EI — Calculates (one point) Expected improvement.
Ei=EI(opt,x)
mlist of type EGO.
matrix (mx,nx) of points at which calculates (one point) Ei, mx rows for mx data points, nx columns for each dimension.
expected improvement at points x.
// 1D example function [y]=gpeak(x) y=sin(x*3)-exp(-(x+0.1)^2/0.01) endfunction; ftest=gpeak; x_bound=[-1; 1]; noise=0; X=(linspace(x_bound(1),x_bound(2),6))';// six initial points YExp=ftest(X); // response Xtest=(linspace(x_bound(1),x_bound(2),100))'; // test points // creaate initial kriging model [kmodel] =km(X,YExp,0,'gaussian',1,0.0000001); kmodel.estimateNoise=0; [kmodel p]=findTheta(kmodel,0,5,'MLL','RS',100); // ego boundaries lob=[-1]; upb=[1]; maxit=16; opt=EGO(kmodel,lob,upb,maxit,0.00000001,%t,1); x=RLHS(10,1,lob,upb); EI(opt,x) scf(); plot(Xtest,EI(opt,Xtest));