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

Neural network learning with global heuristic search.

Ivan Jordanov, Antoniya Georgieva

    IEEE Transactions on Neural Networks
    |May 29, 2007
    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

    Fetal monitoring for high-risk pregnancies using a wearable ultrasound patch.

    Nature biotechnology·2026
    Same author

    Author Reply.

    BJOG : an international journal of obstetrics and gynaecology·2026
    Same author

    Fetal monitoring using a wearable ultrasound patch for high-risk pregnancies.

    Research square·2025
    Same author

    Revisiting the Value of Admission Cardiotocography in Term Pregnancies: An Updated Systematic Review and Meta-Analysis.

    BJOG : an international journal of obstetrics and gynaecology·2025
    Same author

    Advancements in Fetal Heart Rate Monitoring: A Report on Opportunities and Strategic Initiatives for Better Intrapartum Care.

    BJOG : an international journal of obstetrics and gynaecology·2025
    Same author

    The peripheral chemoreflex and fetal defenses against intrapartum hypoxic-ischemic brain injury at term gestation.

    Seminars in fetal & neonatal medicine·2024

    A new hybrid global optimization (GO) algorithm, LP(tau)NM, effectively trains feedforward neural networks (NNs) by combining low-discrepancy sequences and simplex search for improved supervised learning.

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Optimization Algorithms

    Background:

    • Investigates a novel hybrid global optimization (GO) algorithm for supervised learning in feedforward neural networks (NNs).
    • The algorithm, LP(tau)NM, aims to determine network weights by minimizing the mean square error function.
    • It integrates a global heuristic search using LPtau low-discrepancy sequences with a simplex local search.

    Discussion:

    • The LP(tau)NM algorithm's performance is evaluated on multimodal mathematical functions.
    • It is then applied to train moderate-sized NNs for benchmark problems.
    • Results are analyzed and compared against established methods like backpropagation (BP) and differential evolution.

    Key Insights:

    • The hybrid LP(tau)NM algorithm demonstrates a viable approach for optimizing neural network training.

    Related Experiment Videos

  • Integration of low-discrepancy sequences offers a novel strategy within global optimization for NNs.
  • Comparative analysis highlights potential advantages over traditional and other evolutionary optimization techniques.

    • Outlook:

    • Further research could explore LP(tau)NM on larger and more complex neural network architectures.
    • Investigating parameter tuning for LP(tau)NM may yield enhanced performance across diverse datasets.
    • Potential applications in various machine learning tasks beyond benchmark problems warrant exploration.