Gaussian Processes Regression(GPR) 高斯过程回归 Matlab 实现

高斯过程回归（GPR）的matlab 实现， Matlab 为实现高斯过程回归提供了接口函数 fitrgp, 详细参考fitrgp官方文档 非常详细[4]

语法: 

gprMdl = fitrgp(tbl,ResponseVarName)

gprMdl = fitrgp(tbl,formula)

gprMdl = fitrgp(tbl,y)

gprMdl = fitrgp(X,y)

gprMdl = fitrgp(___,Name,Value)

Example 1 :

这个例子用到鲍鱼数据[1],[2], 来自于知识库[3]来预测鲍鱼的年龄. 下载数据保存到你当前的文件夹命名 'abalone.data'.

tbl = readtable('abalone.data','Filetype','text',...
     'ReadVariableNames',false);
tbl.Properties.VariableNames = {'Sex','Length','Diameter','Height',...
     'WWeight','SWeight','VWeight','ShWeight','NoShellRings'};
tbl(1:7,:)

gprMdl = fitrgp(tbl,'NoShellRings','KernelFunction','ardsquaredexponential',...
      'FitMethod','sr','PredictMethod','fic','Standardize',1)
  
ypred = resubPredict(gprMdl);

figure();
plot(tbl.NoShellRings,'r.');
hold on
plot(ypred,'b');
xlabel('x');
ylabel('y');
legend({'data','predictions'},'Location','Best');
axis([0 4300 0 30]);
ho