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

Ensemble-based control of evolutionary optimization algorithms.

Axel Reimann1, Werner Ebeling

  • 1Humboldt-University Berlin, Institute of Physics, D-10115 Berlin, Germany.

Physical Review. E, Statistical, Nonlinear, and Soft Matter Physics
|May 15, 2002
PubMed
Summary
This summary is machine-generated.

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

Intrinsic electronic noise strength significantly alters a period doubling cascade to chaos.

Chaos (Woodbury, N.Y.)·2021
Same author

Active particles with broken symmetry.

Chaos (Woodbury, N.Y.)·2012
Same author

Harmonic oscillator under Lévy noise: unexpected properties in the phase space.

Physical review. E, Statistical, nonlinear, and soft matter physics·2011
Same author

Anharmonicity and its significance to non-Ohmic electric conduction.

Physical review. E, Statistical, nonlinear, and soft matter physics·2006
Same author

New species in evolving networks--stochastic theory of sensitive networks and applications on the metaphorical level.

Bio Systems·2006
Same author

Noise-induced transition from translational to rotational motion of swarms.

Physical review. E, Statistical, nonlinear, and soft matter physics·2005

This study introduces automatic control for evolutionary optimization algorithms. A narrow parameter window, guided by fitness dispersion and entropy, optimizes mutation rate and temperature for better results.

Area of Science:

  • Computational Intelligence
  • Bioinformatics
  • Optimization Algorithms

Background:

  • Evolutionary optimization algorithms rely on intrinsic search parameters.
  • Manual tuning of these parameters is often suboptimal and time-consuming.
  • Adaptive control methods are needed for robust optimization performance.

Purpose of the Study:

  • To develop an automatic control method for intrinsic search parameters in evolutionary optimization.
  • To identify a narrow parameter window that ensures effective optimization.
  • To adapt the algorithm's search behavior based on fitness dispersion.

Main Methods:

  • Implementing a control sensor based on an entropy measure.
  • Steering the ensemble's fitness dispersion to adapt parameter values.

Related Experiment Videos

  • Testing the method on artificial (low autocorrelated binary strings) and natural (RNA) sequences.

    • Main Results:

    • Demonstrating that a small search parameter window yields superior optimization outcomes.
    • Showing the effectiveness of entropy-based control for adapting mutation rate and temperature.
    • Validating the approach on diverse sequence optimization tasks.

    Conclusions:

    • Automatic control of evolutionary algorithm parameters is feasible and efficient.
    • Fitness dispersion steering via entropy provides robust adaptation.
    • The proposed method enhances optimization for both artificial and biological sequences.