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

Fast modular network implementation for support vector machines.

Guang-Bin Huang1, K Z Mao, Chee-Kheong Siew

  • 1School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798, Singapore. gbhuang@ieee.org

IEEE Transactions on Neural Networks
|December 14, 2005
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

Artificial Intelligence Diagnosis of Obstructive Sleep Apnea Using Overnight Pulse Oximetry: A Systematic Review and Bayesian Meta-Analysis.

Journal of medical Internet research·2026
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

Artificial Intelligence Diagnosis of Obstructive Sleep Apnoea using Overnight Pulse Oximetry: A Systematic Review and Bayesian Meta-Analysis.

Journal of medical Internet research·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

This study introduces a novel modular network architecture using multiple Support Vector Machines (SVMs) to efficiently handle large, complex datasets. This approach significantly speeds up training time for SVM algorithms without compromising performance.

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Computational Science

Background:

  • Support Vector Machines (SVMs) are widely applied but struggle with large, complex datasets due to computationally intensive training.
  • Training SVMs involves algorithms with at least quadratic complexity relative to the number of training examples, limiting scalability.

Purpose of the Study:

  • To propose a new, efficient network architecture for Support Vector Machines (SVMs) to overcome computational challenges in large-scale problems.
  • To reduce the learning time of SVM algorithms while maintaining generalization performance.

Main Methods:

  • Developed a modular network architecture comprising multiple SVMs, each trained on distinct subregions of the data space.
  • Integrated simple neural quantizer modules to manage SVM outputs, ensuring only a single local SVM is active at any time.

Related Experiment Videos

  • Implemented a region-computing based approach for modular networks.

    • Main Results:

    • The proposed modular network architecture significantly reduces the computational time required for training SVMs on large datasets.
    • Experimental results on benchmark problems demonstrate substantial speed improvements compared to single SVMs.
    • Generalization performance was largely maintained, showing minimal sacrifice despite the efficiency gains.

    Conclusions:

    • The region-computing based modular network method offers an efficient alternative for applying SVMs to large and complex problems.
    • This approach effectively addresses the scalability limitations of traditional SVM training algorithms.
    • The method provides a practical solution for faster machine learning model development without significant performance trade-offs.