Loading ...
Sorry, an error occurred while loading the content.

Multimodal Optimization: A fundamental Question

Expand Messages
  • Varun Aggarwal
    Hello For the past some time I have been working on multimodal GAs and wanted to discuss some doubts and observations about them. The fundamental question,
    Message 1 of 1 , Aug 1, 2002
    • 0 Attachment
      Hello
       
      For the past some time I have been working on multimodal GAs and wanted to discuss some doubts and observations about them.
       
      The fundamental question, which arises in my mind is which sets of points are actually desired at the end of the search, are they solutions with a high fitness value or points located on peaks? There is a large difference between the two. A peaks may have a low fitness value, but will always follow the characterstic that points adjacent to it will have lower fitness as compared to them. And my study of previous works on multimodal GAs show that the functions on which experiments were conducted, the desired idea was to find all the peaks rather than points with high fitness value.
       
      On the other hand, techniques generally being designed for multimodal problems continue to concentrate on high fitness value to choose individuals rather than having a look at the fitness of indviduals around a point. This basic error is approach gives rise to problems such as need for value of niche radius to run the algorithm properly, algorithmic complexity, etc.
       
      Considering the problem of maxima searching, an approach to consider the value of the function for the points around an individual to decide is fitness looks fundamentally more impressive. The core idea is to shift the idea of fitness from absolute function value to 'relative function value' (incremental function value from neighbouring points). It could be like turning attention from the function to its derivative!!!
       
      I dont dare suggest a complete banishment of idea of fitness value decided by function value, because it may mean a complete change in the basic SGA and its effect, I can't contemplate. But a decent change in the fitness function or employment of a hybrid scheme on basis of this concept looks fundamentally more strong and may render better results.
       
      Any takers for this idea. Or am I making some basic error.
       
      Eagerly waiting for your comments.
          
      With regards
      Varun Aggarwal
       
    Your message has been successfully submitted and would be delivered to recipients shortly.