HOME   ::  Conference List   ::   Conference Paper
Angeline, P. J. and Pollack, J. B. (1994) Coevolving High-Level Representations. In C. Langton, editor, Artificial Life III, pages 55--71. Reading MA: Addison-Wesley.
Bookmark:  

Full-text
   URL: http://www.natural-selection.com/people/pja/docs/alife3.ps.Z
   Cached: PDF-44K    PS-164K    PS.gz-45K   
   SAVE AS an easy-to-recall long filename:
      Filename format: author--year--title   PDF-44K    PS-45K    :: About GZip'd PS
      Filename format: author--year--title--journal|proceedings|...--pages   PDF-44K    PS-45K   

Related links
   CiteSeer: http://citeseer.ist.psu.edu/angeline94coevolving.html
  Web search: Google Web Search   ::   Google Scholar
  Within this site: References (25)

Paper at a Glance 

Coevolving High­Level Representations
Peter J. Angeline and Jordan B. Pollack
Laboratory for Artificial Intelligence Research
Computer and Information Science Department
The Ohio State University
Columbus, Ohio 43210
pja@cis.ohio­state.edu
pollack@cis.ohio­state.edu
To Appear in:
Artificial Life III
The Ohio State University January 17, 1996 1
Coevolving High­Level Representations
Peter J. Angeline and Jordan B. Pollack
Laboratory for Artificial Intelligence Research
Computer and Information Science Department
The Ohio State University
Columbus, Ohio 43210
pja@cis.ohio­state.edu
pollack@cis.ohio­state.edu
Abstract Several evolutionary simulations allow for a dynamic resizing of the genotype. This is an important alternative to constraining the genotype's maximum size and complexity. In this paper, we add an additional dynamic to simulated evolution with the description of a genetic algorithm that coevolves its representation language with the genotypes. We introduce two mutation operators that permit the acquisition of modules from the genotypes during evolution. These modules form an increasingly high­ level representation language specific to the developmental environment. Experimental results illustrating interesting properties of the acquired modules and the evolved languages are provided.
1.0 Introduction A central theme of artificial life is to construct artifacts that approach the complexity of biological systems. To accomplish this, the benefits and limitations of current methods and tools must be considered. The representation employed in a genetic algorithm, for example, must permit an appropriate level of expression in order for the genotypes to evolve. 22,18 Artificial life researchers favor genetic algorithms both for their proven ability in wide range of environments and for their obvious association with natural evolution. However, in most genetic algorithms, the representation's length is fixed a priori, placing an ad hoc restriction on the ...
BibTex
@inproceedings{angeline94coevolvingHigh,
  author={Peter J. Angeline and Jordan B. Pollack},
  title={Coevolving High-Level Representations},
  year={1994},
  pages={55-71},
  address={Reading MA},
  editor={C. Langton},
  publisher={Addison-Wesley},
  booktitle={Artificial Life III},
  url={http://www.isrl.uiuc.edu/~amag/langev/paper/angeline94coevolvingHigh.html}
}

 HOME   ::  Conference List   ::   Conference Paper Comments to: junwang4 you-know-at gmail.com Last update: 2/2/08