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

Binary tree of SVM: a new fast multiclass training and classification algorithm.

Ben Fei1, Jinbai Liu

  • 1Department of Mathematics, Tongji University, Shanghai 200092, China. feibenalgebra@hotmail.com

IEEE Transactions on Neural Networks
|May 26, 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

Metal Single Atoms Beyond Catalysis as Quantum Modulators for Programmable Electronic Structures and Adaptive Electronics.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Assessing the tourism impacts of urban marathon events in central China's historic cities: a residents' SEM analysis.

Frontiers in sports and active living·2026
Same author

Physically consistent global atmospheric data assimilation with machine learning in latent space.

Science advances·2026
Same author

Toward a Unified Representation of Multi-Modal Pre-Training for 3-D Processing.

IEEE transactions on visualization and computer graphics·2025
Same author

GetMesh: A Controllable Model for High-quality Mesh Generation and Manipulation.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

A diffusion model for universal medical image enhancement.

Communications medicine·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

We introduce Binary Tree of support vector machine (SVM), or BTS, a novel architecture for efficient multiclass classification. BTS significantly reduces classifiers, offering faster training and classification, especially for large datasets.

Area of Science:

  • Machine Learning
  • Computer Science

Background:

  • Multiclass classification problems pose significant computational challenges.
  • Existing methods like Directed Acyclic Graph SVM (DAGSVM) and Error Correcting Output Codes (ECOC) can be inefficient for large numbers of classes.

Purpose of the Study:

  • To introduce a new architecture, the Binary Tree of Support Vector Machine (BTS), for enhanced multiclass classification efficiency.
  • To demonstrate the effectiveness of BTS and its enhanced version, c-BTS, in reducing the number of binary classifiers required.

Main Methods:

  • The proposed Binary Tree of Support Vector Machine (BTS) architecture organizes classifiers in a tree structure.
  • BTS and c-BTS aim to minimize the number of binary classifiers needed for multiclass problems.
  • Analysis of training complexity and decision-making convergence complexity is performed.

Related Experiment Videos

Main Results:

  • BTS achieves N-1 binary classifiers in the best training scenario (N=number of classes).
  • Decision-making involves logarithmic complexity, specifically log4/3((N+3)/4) binary tests on average.
  • Experiments show BTS training is significantly faster than existing methods with comparable accuracy.

Conclusions:

  • BTS offers a highly efficient solution for multiclass classification problems.
  • The logarithmic complexity of BTS makes it particularly advantageous for classification tasks with a large number of classes.
  • BTS provides a faster alternative to DAGSVM and ECOC for large-scale multiclass classification.