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 hybrid neural learning algorithm using evolutionary learning and derivative free local search method.

Ranadhir Ghosh1, John Yearwood, Moumita Ghosh

  • 1School of Information Technology and Mathematical Sciences, University of Ballarat, P.O. Box 663, Victoria, Australia. r.ghosh@ballarat.edu.au

International Journal of Neural Systems
|October 19, 2006
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

Connexin 43 Loss in Endothelial Progenitors Facilitates Functional Airway Adaptation After Lung Injury.

Research square·2026
Same author

Modified Single-Puncture Temporomandibular Joint (TMJ) Arthrocentesis Using a Spinal Needle: A Case Report.

Cureus·2026
Same author

A CHEF-driven fluorescent turn-on probe for sensitive and rapid Al<sup>3+</sup> detection in live MDA-MB-231 cells.

Analytical methods : advancing methods and applications·2026
Same author

Progenitor Resilience and the Early Onset of Chronic Lung Diseases: NHLBI workshop report.

American journal of respiratory cell and molecular biology·2026
Same author

Asymmetry to Symmetry: A Case Report of Mandibular Asymmetry Managed With Distraction Osteogenesis Followed by Genioplasty.

Cureus·2026
Same author

A novel pyrophosphatase activity of SiaD, a diguanylate cyclase of Pseudomonas aeruginosa.

Biochemical and biophysical research communications·2026
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

This study introduces hybrid models combining Discrete Gradient and evolutionary strategies for artificial neural network weight optimization. These hybrid approaches significantly accelerate finding optimal solutions compared to individual methods.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Optimization

Background:

  • Artificial neural networks (ANNs) require efficient weight optimization.
  • Discrete Gradient methods excel at escaping local minima but benefit from good initializations.
  • Evolutionary algorithms are robust global optimizers but suffer from long training times, limiting real-world applications.

Purpose of the Study:

  • To investigate hybrid models integrating Discrete Gradient methods and evolutionary strategies for ANN weight optimization.
  • To explore and compare different fusion strategies for these hybrid models.
  • To enhance the speed and efficiency of ANN training for large-scale problems.

Main Methods:

  • Developing hybrid models combining Discrete Gradient and evolutionary strategies.

Related Experiment Videos

  • Implementing three distinct fusion strategies: linear, iterative, and restricted local search.
  • Evaluating model performance on standard datasets for weight optimization tasks.

    • Main Results:

    • Hybrid models demonstrate faster convergence towards optimal solutions compared to standalone methods.
    • Different fusion strategies show varying effectiveness, with specific models outperforming others on certain datasets.
    • The proposed hybrid approach addresses the time complexity limitations of evolutionary algorithms.

    Conclusions:

    • Hybrid Discrete Gradient and evolutionary strategy models offer a promising approach for efficient ANN weight optimization.
    • The choice of fusion strategy is critical for achieving optimal performance.
    • These hybrid models present a viable solution for real-world applications where training time is a key constraint.