How can I view the automatically generated initial population from GA in Global Optimization Toolbox?

3 views (last 30 days)
I am using the GA function in the Optimization Toolbox, and I'm trying to figure out how I can see the initial population that MATLAB created for me. Any tips on that?

Accepted Answer

Prabhakar
Prabhakar on 18 Jan 2011
To see the intial population, one can specify/set the 'OutputFcns' property from the option used by GA. The function set by 'OutputFcns' gets called every itteration. First write a function MATLAB file called my_view containing
function [state, options,optchanged] = my_view(options,state,flag,interval)
optchanged = false;
disp(state.Population)
end
Now set the 'OutputFcns' property to this function via
options = gaoptimset('OutputFcns',@my_view);
Finally call the GA function with this specified option
x = ga(fitnessfcn,nvars,options)
  2 Comments
saranya thangavel
saranya thangavel on 30 Jan 2014
i am using GA for feture selection,i need to specify my features in initial population.features are in double vectore format.can u tell me how to specify those values in initial population? i need format,i am using matlab12b optimization toolbox
Igor
Igor on 30 Jan 2014
saranya thangavel,
I might not have understood what you mean, but if you need to pass your initial population instead of having GA produce it for you using a creation function, this can be done with the Initial population option. From the help:
Initial population (InitialPopulation) specifies an initial population for the genetic algorithm. The default value is [], in which case ga uses the default Creation function to create an initial population. If you enter a nonempty array in the Initial population field, the array must have no more than Population size rows, and exactly Number of variables columns. In this case, the genetic algorithm calls a Creation function to generate the remaining individuals, if required.
Then use something like
options = gaoptimset('InitialPopulation', Your_population)
and call GA with this options structure.
You can also write your own creation function.

Sign in to comment.

More Answers (0)

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!