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 real-coded genetic algorithm for training recurrent neural networks.

A Blanco1, M Delgado, M C Pegalajar

  • 1Department of Computer Science and Artificial Intelligence, ETSI Informática, University of Granada, Spain.

Neural Networks : the Official Journal of the International Neural Network Society
|February 24, 2001
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

Quantification of Sonicated Implants from Patients with Osteoarticular Implant Infections.

Antibiotics (Basel, Switzerland)·2026
Same author

Genome-wide association study identifies QTL and candidate genes for grain size and weight in a Triticum turgidum collection.

The plant genome·2025
Same author

Headache as main reason for consultation to a hospital Emergency Department in Spain: a prospective study.

Neurologia·2024
Same author

Towards energy efficiency: A comprehensive review of deep learning-based photovoltaic power forecasting strategies.

Heliyon·2024
Same author

Dataset for facilitating the calculation of aspect ratio of fibrillated cellulose suspensions based on gel point data.

Data in brief·2024
Same author

A parsimonious methodological framework for short-term forecasting of groundwater levels.

The Science of the total environment·2023
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

New results on prescribed-time synchronization of complex networks via intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Variance-constrained multi-view ensemble broad network for imbalanced data.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces a Real-Coded Genetic Algorithm to train Recurrent Neural Networks, overcoming the instability and computational demands of traditional error gradient methods. The new algorithm shows promise for fuzzy grammatical inference tasks.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Recurrent Neural Networks (RNNs) are less utilized than Feedforward Neural Networks due to training challenges.
  • Gradient-based training algorithms for RNNs exhibit instability and high computational costs, especially with numerous neurons.
  • Existing training methods for RNNs necessitate the development of novel, more robust tools.

Purpose of the Study:

  • To introduce a new training tool for Recurrent Neural Networks.
  • To address the limitations of traditional gradient-based training algorithms.
  • To apply a novel algorithm for fuzzy grammatical inference.

Main Methods:

  • Development of a Real-Coded Genetic Algorithm (GA) specifically designed for training RNNs.

Related Experiment Videos

  • Utilization of appropriate genetic operators tailored for the real-coded encoding type.
  • Experimental comparison of the proposed GA against the Real-Time Recurrent Learning (RTRL) algorithm.

    • Main Results:

    • The Real-Coded Genetic Algorithm provides a stable and efficient method for training Recurrent Neural Networks.
    • The GA demonstrates effectiveness in performing fuzzy grammatical inference.
    • The proposed GA offers a viable alternative to conventional, less stable training algorithms.

    Conclusions:

    • The developed Real-Coded Genetic Algorithm is an effective tool for training Recurrent Neural Networks.
    • This approach overcomes the inherent instability and computational burden associated with gradient-based methods.
    • The GA shows significant potential for applications such as fuzzy grammatical inference.