MATLAB Answers

Hello everyone! this is the first time I am using GA and I encountered with this message:Failure in initial user-supplied fitness function evaluation. GA cannot continue.

2 views (last 30 days)
here is my codes.
k1=0.6;
k2=0.25;
k3=0.15;
[x,fval] = ga(@(f)myfcn(f(1),f(2),f(3)),3)
function t=myfcn(f)
t=(k1*f(1)+k2*f(2)+k3*f(3));
end
%%all f values have been attained in another code
can anyone help me with this?

Accepted Answer

Geoff Hayes
Geoff Hayes on 25 Mar 2020
Edited: Geoff Hayes on 25 Mar 2020
amir - you don't need to supply the f, those f values that have been attained in another code. The genetic algorithm will provide those from the initial population and from the subsequent generations (via crossover and mutation). All you need to do is pass in the function handle like
[x,fval] = ga(@myfcn, 3)
Since your myfcn depends upon the k1, k2, and k3, then ensure that your fitness function is nested within the main function
function main
k1=0.6;
k2=0.25;
k3=0.15;
[x,fval] = ga(@myfcn,3)
function t=myfcn(f)
t=(k1*f(1)+k2*f(2)+k3*f(3));
end
end
and saved (in this case) to a file named main.m. (Perhaps you have already done this.)

  12 Comments

Show 9 older comments
amir hosseini
amir hosseini on 25 Mar 2020
thank you very much indeed dear Geoff that was really nice of you!
will you please send me an empty email to amirhsn51@gmail.com please?
amir hosseini
amir hosseini on 25 Mar 2020
yes thank you that is understandable. I wanted to make an offer of working together and expand my article to publish it soon.
I would really appreciate it if you let me know in case of your willingness by personal email.
yours truly!

Sign in to comment.

More Answers (0)

Sign in to answer this question.