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

An alternative approach for neural network evolution with a genetic algorithm: crossover by combinatorial

Nicolás García-Pedrajas1, Domingo Ortiz-Boyer, César Hervás-Martínez

  • 1Department of Computing and Numerical Analysis, University of Córdoba, 14071 Córdoba, Spain. npedrajas@uco.es

Neural Networks : the Official Journal of the International Neural Network Society
|December 14, 2005
PubMed
Summary

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

Convolutional- and Deep Learning-Based Techniques for Time Series Ordinal Classification.

IEEE transactions on cybernetics·2025
Same author

Gender-Equity Model for Liver Allocation Using Artificial Intelligence (GEMA-AI) for Waiting List Liver Transplant Prioritization.

Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association·2025
Same author

Machine Learning Algorithms in Controlled Donation After Circulatory Death Under Normothermic Regional Perfusion: A Graft Survival Prediction Model.

Transplantation·2025
Same author

Deep Ordinal Classification in Forest Areas Using Light Detection and Ranging Point Clouds.

Sensors (Basel, Switzerland)·2024
Same author

Learning Ordinal-Hierarchical Constraints for Deep Learning Classifiers.

IEEE transactions on neural networks and learning systems·2024
Same author

Cluster analysis and forecasting of viruses incidence growth curves: Application to SARS-CoV-2.

Expert systems with applications·2023

This study introduces a novel crossover operator for evolving neural networks, overcoming the permutation problem. The new method enhances evolutionary programming by creating smaller, high-performing networks.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • Evolutionary programming is favored for neural network evolution due to issues with traditional crossover operators.
  • The permutation problem, where identical networks have multiple genetic representations, hinders crossover's effectiveness.

Purpose of the Study:

  • To develop a new crossover operator for genetic neural network evolution that addresses the permutation problem.
  • To improve the efficiency and performance of evolutionary algorithms in neural network design.

Main Methods:

  • A modified crossover operator is proposed, considering the specific structure of neural network individuals.
  • The approach redefines crossover as a combinatorial optimization problem, focusing on selecting near-optimal hidden layer projections.

Related Experiment Videos

  • The new operator was tested against classical crossover on 25 real-world problems.

    • Main Results:

    • The novel crossover operator demonstrated excellent performance across 25 real-world problems.
    • Networks evolved using the new approach were significantly smaller than those from classical crossover.
    • The method effectively mitigates the permutation problem in neural network genetic evolution.

    Conclusions:

    • The proposed crossover operator offers a more effective and efficient method for evolving neural networks.
    • This advancement in evolutionary computation can lead to more compact and performant neural network architectures.
    • The combinatorial optimization formulation provides a robust solution for crossover in neural network genetic algorithms.