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

Branching competitive learning network: a novel self-creating model.

Huilin Xiong1, M N S Swamy, M Omair Ahmad

  • 1Center for Signal Processing and Communications, Department of Electrical and Computer Engineering, Concordia University, Montreal, QC H3G 1M8, Canada. hlxiong@ece.concordia.ca

IEEE Transactions on Neural Networks
|September 24, 2004
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

A Functional Shape Framework for the Detection of Multiple Sclerosis Using Optical Coherence Tomography Images.

Sensors (Basel, Switzerland)·2026
Same author

SCMBench: benchmarking domain-specific and foundation models for single-cell multi-omics data integration.

Nature communications·2026
Same author

A Survey on Vision-Language-Action Models for Embodied AI.

IEEE transactions on neural networks and learning systems·2026
Same author

INNFusion: A Diffusion-Based Blind Image Super Resolution Scheme Using Reversible Degradation Process With Invertible Neural Networks.

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

HC-GLAD: Dual hyperbolic contrastive learning for unsupervised graph-level anomaly detection.

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

Recent Advances of Multimodal Continual Learning: A Comprehensive Survey.

IEEE transactions on neural networks and learning systems·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 Branching Competitive Learning (BCL), a novel self-creating neural network model. BCL enhances data clustering and quantization by efficiently capturing spatial data distributions.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Self-creating neural network models are crucial for adaptive data analysis.
  • Competitive learning models offer robust clustering but can lack adaptability.
  • Existing models often struggle with dynamic data distributions and determining optimal cluster numbers.

Purpose of the Study:

  • To introduce a novel self-creating neural network model called Branching Competitive Learning (BCL).
  • To enhance the efficiency and accuracy of data clustering and quantization.
  • To demonstrate the model's capability in estimating cluster numbers and adapting to nonstationary data.

Main Methods:

  • Incorporation of a branching mechanism within a competitive learning framework.

Related Experiment Videos

  • Development of a unique node-splitting criterion based on geometrical measurements of synaptic vector movement in weight space.
  • Comparative analysis against other self-creating and non-self-creating competitive learning models.

    • Main Results:

    • The BCL network demonstrates superior efficiency in capturing the spatial distribution of input data.
    • BCL achieves improved clustering and quantization results compared to existing models.
    • The model effectively estimates the cluster number, adapts to nonstationary data, and enables multiresolution clustering.

    Conclusions:

    • Branching Competitive Learning (BCL) offers a significant advancement in self-creating neural networks.
    • BCL provides enhanced performance for data clustering and quantization, particularly with complex and dynamic datasets.
    • The algorithm's effectiveness is validated through extensive experiments in image compression vector quantization.