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

Forming neural networks through efficient and adaptive coevolution

Moriarty1, Miikkulainen

  • 1Information Sciences Institute, University of Southern California, Marina del Rey 90292, USA. moriarty@isi.edu

Evolutionary Computation
|January 1, 1997
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

Infusions of local anaesthetic via caudal catheters in neonates and small infants for analgesia after major surgery

Paediatric anaesthesia·2000
Same author

An audit of the last seven years of paediatric anaesthetic airway problems in patients on the birmingham bone anchored hearing aid (BAHA) programme

Paediatric anaesthesia·2000
Same author

Laparoscopic versus open appendectomy.

Current surgery·2000
Same author

Simultaneous X-Ray and TeV Observations of a Rapid Flare from Markarian 421.

The Astrophysical journal·1999
Same author

Resonant magnetotunneling through individual self-assembled InAs quantum dots.

Physical review. B, Condensed matter·1996
Same author

Atomistic simulation of ideal shear strength, point defects, and screw dislocations in bcc transition metals: Mo as a prototype.

Physical review. B, Condensed matter·1996
Same journal

Computing Optimal Populations for Binary Problems using Logic Minimization.

Evolutionary computation·2026
Same journal

Enhancing Generalization and Scalability for Multi-Objective Optimization with Population Pre-Training.

Evolutionary computation·2026
Same journal

XCS for Sequential Perceptual Aliasing in Multi-Step Decision Making.

Evolutionary computation·2026
Same journal

A dynamic multi-objective evolutionary algorithm using dual-space prediction and surrogate-based sampling.

Evolutionary computation·2026
Same journal

Adapting MOEA/D to CMA-ES for Dealing with Ill-conditioned Multiobjective Problems.

Evolutionary computation·2026
Same journal

Editorial of the Special Issue: Parallel Problem Solving from Nature PPSN 2024 Extended Versions of Best Paper Candidates.

Evolutionary computation·2026
See all related articles

Symbiotic adaptive neuroevolution (SANE) enhances difficult control problems by coevolving cooperating neurons. This approach offers greater efficiency, adaptability, and diversity compared to traditional methods.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Evolutionary Computation

Background:

  • Traditional neural network approaches often struggle with complex control tasks.
  • Population-based methods can be inefficient and lack diversity.
  • Cooperative and coevolutionary strategies offer potential improvements.

Purpose of the Study:

  • To demonstrate the advantages of cooperative, coevolutionary search for challenging control problems.
  • To introduce and evaluate the Symbiotic Adaptive Neuroevolution (SANE) system.
  • To analyze emergent neuron specializations and roles within the SANE system.

Main Methods:

  • Utilizing the Symbiotic Adaptive Neuroevolution (SANE) system.
  • Coevolving a population of neurons to form cooperative neural networks.

Related Experiment Videos

  • Comparing SANE's performance against network-based population approaches.

    • Main Results:

    • SANE demonstrates superior efficiency and adaptability in difficult control problems.
    • The SANE system maintains higher levels of population diversity.
    • Empirical studies reveal emergent specialization and distinct roles among neurons.

    Conclusions:

    • Cooperative, coevolutionary search, as implemented by SANE, is advantageous for complex control tasks.
    • SANE provides a robust encoding of control behavior through specialized, cooperating neurons.
    • The SANE system offers a more effective and diverse alternative to conventional methods.