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 forward algorithm for RBF neural network construction.

Jian-Xun Peng1, Kang Li, De-Shuang Huang

  • 1School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, Belfast BT9 5AH, UK. k.li@qub.ac.uk

IEEE Transactions on Neural Networks
|November 30, 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

Human-Structure-Aware Token Position Embedding for Tokenized Pose Estimation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

GraphLooper: predicting chromatin loops based on hierarchical multi-view graph pooling method.

Briefings in bioinformatics·2026
Same author

LMSCDA: A Secondary Structure Enhanced Language Model for Predicting CircRNA and Disease Associations.

IEEE journal of biomedical and health informatics·2026
Same author

Multi-species integration, alignment and annotation of single-cell RNA-seq data with CAMEX.

Nature communications·2026
Same author

SpaLSTF: Diffusion-based generative model with BiLSTM and XCA-Transformer for spatial transcriptomics imputation.

PLoS computational biology·2026
Same author

A scalable computational framework for predicting gene expression from candidate <i>cis</i>-regulatory elements.

Genome research·2026
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 hybrid forward algorithm (HFA) for building radial basis function (RBF) neural networks. The HFA efficiently creates parsimonious RBF networks with tunable nodes, improving performance and reducing memory needs.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Radial Basis Function (RBF) neural networks are powerful tools for complex function approximation.
  • Constructing parsimonious RBF networks with optimal structure and parameters remains a significant challenge.
  • Existing methods often struggle with the mixed-integer nature of simultaneous structure and parameter optimization.

Purpose of the Study:

  • To propose a novel hybrid forward algorithm (HFA) for the efficient construction of RBF neural networks.
  • To achieve simultaneous network structure determination and parameter optimization in the continuous parameter space.
  • To develop a parsimonious RBF network that exhibits enhanced generalization capabilities.

Main Methods:

  • Development of a hybrid forward algorithm (HFA) integrating analytic frameworks.

Related Experiment Videos

  • Simultaneous optimization of network structure and parameters within a continuous parameter space.
  • Computational complexity analysis to evaluate algorithmic efficiency.

    • Main Results:

    • The proposed HFA effectively addresses the mixed-integer hard problem of RBF network construction.
    • Significant improvements in network performance and reduced memory usage were observed.
    • Computational complexity analysis confirmed the algorithm's efficiency.

    Conclusions:

    • The HFA provides an efficient and effective method for constructing parsimonious RBF neural networks.
    • The algorithm demonstrates superior performance and memory efficiency compared to existing approaches.
    • This work contributes a valuable tool for developing well-generalizing RBF networks.