Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A statistical study of a class of cellular evolutionary algorithms.

M Capcarrère1, M Tomassini, A Tettamanzi

  • 1Logic Systems Laboratory, Swiss Federal Institute of Technology, 1015 Lausanne, Switzerland. Mathieu.Capcarrere@epfl.ch.

Evolutionary Computation
|September 24, 1999
PubMed
Summary

This study introduces statistical measures to analyze cellular evolutionary algorithms. These measures reveal common trends and problem-specific features, aiding in understanding algorithm phases.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Degree correlations in random geometric graphs.

Physical review. E, Statistical, nonlinear, and soft matter physics·2012
Same author

Dynamics of unperturbed and noisy generalized Boolean networks.

Journal of theoretical biology·2009
Same author

Thrombolysis in ST-segment elevation myocardial infarction: potential role of thin-slice computed tomography in the assessment of reperfusion and plaque characterization.

Clinical cardiology·2006
Same author

Evaluation of venous and arterial conduit patency by 16-slice spiral computed tomography.

Circulation·2004
Same author

Multidetector row CT coronary angiography: technique and preliminary experience.

La Radiologia medica·2002
Same author

Necessary conditions for density classification by cellular automata.

Physical review. E, Statistical, nonlinear, and soft matter physics·2001

Area of Science:

  • Computational intelligence
  • Evolutionary computation
  • Artificial life

Background:

  • Parallel evolutionary algorithms show empirical success but lack in-depth understanding.
  • Cellular (fine-grained) evolutionary models require specific analytical tools.
  • Analyzing genotypic and phenotypic levels is crucial for understanding algorithm dynamics.

Purpose of the Study:

  • To introduce novel statistical measures for analyzing cellular evolutionary algorithms.
  • To demonstrate the application of these measures using the cellular programming evolutionary algorithm.
  • To investigate the behavior of evolutionary algorithms on cellular automata problems.

Main Methods:

  • Development of statistical measures at genotypic and phenotypic levels.

Related Experiment Videos

  • Application of these measures to the cellular programming evolutionary algorithm.
  • Testing on cellular automata problems: density, synchronization, and random number generation.

    • Main Results:

    • Identification of common trends across different problems, suggesting intrinsic algorithm properties.
    • Discovery of problem-specific features influencing algorithm behavior.
    • Quantitative delimitation of distinct phases in the evolutionary algorithm's progression.

    Conclusions:

    • The proposed statistical measures are effective for analyzing fine-grained evolutionary algorithms.
    • The measures provide insights into both general algorithm behavior and problem-specific adaptations.
    • This work contributes to a better understanding of cellular evolutionary algorithms' internal workings.