• Summary
• Related Documents
  • Active Bibliography
  • Co-citation
• Version History

Popular Tags

Add a tag:

No tags have been applied to this document.

BibTeX | Add To MetaCart

@INPROCEEDINGS{Smith99controllingcode,
    author = {Peter Smith},
    title = {Controlling Code Growth in Genetic Programming},
    booktitle = {De Montfort University},
    year = {1999},
    pages = {166--171},
    publisher = {Physica-Verlag}
}

Bookmarks

         

OpenURL

 

Abstract:

It has been known since the early days of Genetic Programming that the evolutionary process tends to stagnate after a certain number of generations. Furthermore, during the evolutionary process, there is an inexorable and sometimes exponential increase in the average size of programs in a population. This has been called bloat. The major cause of this bloat appears to be caused by introns - sections of non-functional code. In this paper introns are categorised and different approaches to the control of code growth are described. Keywords. Genetic Programming, Code Bloat, Introns, Parsimony Pressure 1 Why Control Code Growth? During the process of evolution in genetic programming, the average size of programs has been seen to grow inexorably in size, sometimes exponentially. The principal explanation for code growth is that fitness causes bloat (Langdon and Poli, 1997). However, this is not an explanation of how code grows. Additionally, assuming that code grows over time, then why...

Citations