Convergence in genetic algorithm method
조회 수: 21 (최근 30일)
이전 댓글 표시
Hi
I used the genetic algorithm, in general idea about this method ,the convergence and the number of iteration is related by what?
In other hand how to solve the problem of convergence(number of gradients) ? and how i can control the number of iteration in next picture?
댓글 수: 0
채택된 답변
Walter Roberson
2019년 7월 28일
"I used the genetic algorithm, in general idea about this method ,the convergence and the number of iteration is related by what?"
No-one knows. There have been successful theoretical analysis for genetic algorithm convergence for some kinds of functions, and some functions appear to converge in practice, but for other functions it is not known whether genetic algorithms converge at all.
"In other hand how to solve the problem of convergence(number of gradients) ?"
On the scale of that diagram, the search looks like it might have converged. But remember that there is a large difference between "convergence" and "finding the global minima". You can easily construct functions where the global minima cannot be found through any search algorithm:
f = @(x) 1000 - (x == 0.1688799713442523664497230129200033843517303466796875)
댓글 수: 0
추가 답변 (0개)
참고 항목
카테고리
Help Center 및 File Exchange에서 Genetic Algorithm에 대해 자세히 알아보기
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!