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

Density-driven generalized regression neural networks (DD-GRNN) for function approximation.

John Y Goulermas1, Panos Liatsis, Xiao-Jun Zeng

  • 1Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool L69 3GJ, UK. j.y.goulermas@liverpool.ac.uk

IEEE Transactions on Neural Networks
|December 7, 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

Explainable Lightweight Model Using Low-Rank and Convolutional Block Attention for Pancreatic Cancer Diagnosis.

The international journal of medical robotics + computer assisted surgery : MRCAS·2026
Same author

Bridging the Modality Gap in Medical Vision-Language Models: A Hybrid Contrastive-Optimal Transport Framework for Enhanced Cross-Modal Alignment.

IEEE journal of biomedical and health informatics·2026
Same author

EIT to CT Cross-Modality Translation Using Diffusion Transformer.

IEEE journal of biomedical and health informatics·2026
Same author

To Transfer or Not to Transfer: Unified Transferability Metric and Analysis.

IEEE transactions on cybernetics·2026
Same author

Hybrid lightweight transformer for efficient landslide change detection in remote sensing imagery.

Scientific reports·2025
Same author

2D Time-varying functional modeling framework for multi-scale solar irradiance forecasting.

Neural networks : the official journal of the International Neural Network Society·2025
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces a novel nonparametric regression method using generalized regression neural networks (GRNNs) and density features. The approach reduces computational load and offers competitive accuracy for function approximation.

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Computational Statistics

Background:

  • Nonparametric regression methods are crucial for modeling complex data relationships.
  • Generalized Regression Neural Networks (GRNNs) offer a powerful framework for regression tasks.
  • Managing bandwidth selection in kernel-based methods can be computationally intensive.

Purpose of the Study:

  • To propose a novel, computationally efficient nonparametric regression method.
  • To reduce the number of parameters in GRNNs by using trainable weights.
  • To improve function approximation accuracy while minimizing computational demands.

Main Methods:

  • Combining GRNNs with density-dependent multiple kernel bandwidths.
  • Utilizing extracted data density features to reflect data properties.

Related Experiment Videos

  • Implementing an efficient initialization scheme and a second-order training algorithm.
  • Employing Bayesian regularization for overfitting control.

    • Main Results:

    • The proposed model significantly reduces computational demands compared to methods with individual bandwidths.
    • Achieves competitive function approximation accuracy.
    • Demonstrates effective control of overfitting through Bayesian regularization.

    Conclusions:

    • The novel GRNN-based method offers a more efficient alternative for nonparametric regression.
    • Data density features and trainable weights enhance model performance and reduce complexity.
    • The method provides a strong balance between computational efficiency and approximation accuracy.