Fitness limit check in genetic algorithm

Hello I would just like to make sure the Fitness Limit is actually the value of the fitness function(objective function handle) , so unless GA produced a value smaller than that, the program won't stop, is that correct? The function tolerance doesn't really work for me due to the nature of my problem. My objective function is evaluating the difference between two sets of data, and I'm setting it to be <0.2 for the fitness limit for the stopping criteria. If I use function tolerance it lands on local minima and stops before it actually finds global min (if it has any).any better suggestions? Thank you.

Answer 1

[Nitin Khola]

I am assuming you are using the Optimization app. As per my understanding, you wish to confirm if Fitness Limit is a stopping criterion which is based on the value of fitness function.

Yes, the algorithm stops when the value of the fitness function ( synonymous with objective function ) for the best point in the current population is less than or equal to Fitness limit as mentioned in the following documentation:

http://www.mathworks.com/help/gads/how-the-genetic-algorithm-works.html#f6243

Further, you can also refer to the following documentation for more information on "Global vs. Local Minima Using ga":

http://www.mathworks.com/help/gads/example-global-vs-local-minima-with-ga.html#f12527

[yuese zheng]

thank you for your response. Yes I am using the optimization app. I looked over the global vs local minima using GA, and am wondering what the difference is between "initial range" and the lower bound and upper bound I have set up.

I am also a little confused over the initial population. I have 9 variables, so the default is 200 initial population. Does this mean there are 200 sets of 9 variables generated randomly as long as they are within range? If so, how does it determine which one to pick and go to the next generation?