Difference between revisions of "OoDACE:ooDACE toolbox"

From SUMOwiki
Jump to navigationJump to search
Line 12: Line 12:
  
 
<source lang="matlab">
 
<source lang="matlab">
  startup
+
startup
 
</source>
 
</source>
  
Line 21: Line 21:
  
 
<source lang="matlab">
 
<source lang="matlab">
  ...
+
...
  TODO
+
% Generate kriging options structure
  ...
+
opts = getDefaultOptions();
 +
opts.hpBounds = [lb ; ub]; % hyperparameter optimization bounds
 +
 
 +
% configure the optimization algorithm (only one optimizer is included)
 +
% the Matlab Optimization toolbox is REQUIRED
 +
optimopts.GradObj = 'on';
 +
optimopts.DerivativeCheck = 'off';
 +
optimopts.Diagnostics = 'off';
 +
optimopts.Algorithm = 'active-set';
 +
opts.hpOptimizer = MatlabOptimizer( dim, 1, optimopts );
 +
 
 +
% required BEFORE constructing Kriging class
 +
switch(id)
 +
    case 2
 +
        % add regression parameter
 +
        opts.lambda0 = 0;
 +
        opts.lambdaBounds = [-10 ; 0]; % log scale
 +
    case 3
 +
        % enable blind kriging
 +
        opts.regressionMetric = 'cvpe';
 +
end
 
</source>
 
</source>
  

Revision as of 11:00, 9 February 2010

blindDACE: A versatile kriging Matlab Toolbox

TODO description

Download

See: [[1]]

Quick start guide

IMPORTANT: Before the toolbox can be used you have to include the toolbox in Matlab's path. You can do this manually by running startup or if Matlab is started in the root toolbox directory then startup will be run automatically.

startup


Now the toolbox is ready to be used. The blindDACE toolbox is designed in an object oriented (OO) fashion. It is strongly recommended to exploit the OO design directly, i.e., use the Kriging and Optimizer matlab classes. However, for convenience wrapper scripts (dacefit, predictor) are provided that simulate the DACE toolbox interface (see section TODO for more information).

...
% Generate kriging options structure
opts = getDefaultOptions();
opts.hpBounds = [lb ; ub]; % hyperparameter optimization bounds

% configure the optimization algorithm (only one optimizer is included)
% the Matlab Optimization toolbox is REQUIRED
optimopts.GradObj = 'on';
optimopts.DerivativeCheck = 'off';
optimopts.Diagnostics = 'off';
optimopts.Algorithm = 'active-set';
opts.hpOptimizer = MatlabOptimizer( dim, 1, optimopts );

% required BEFORE constructing Kriging class
switch(id)
    case 2
        % add regression parameter
        opts.lambda0 = 0;
        opts.lambdaBounds = [-10 ; 0]; % log scale
    case 3
        % enable blind kriging
        opts.regressionMetric = 'cvpe';
end

See the included demo.m script for more example code on how to use the blindDACE toolbox.

DACE toolbox interface

dacefit()
predictor()

Contribute

These bindings are very basic but they work for me. Please improve, extend, provide binaries, and of course contribute back.