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

S-TREE: self-organizing trees for data clustering and online vector quantization.

M M Campos1, G A Carpenter

  • 1Center for Adaptive Systems, Department of Cognitive and Neural Systems, Boston University, MA 02215, USA. gail@cns.bu.edu

Neural Networks : the Official Journal of the International Neural Network Society
|June 20, 2001
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

Effect of thermal amplitude on physiological parameters, ruminal fermentation, digestibility, health, and performance of Holstein dairy calves.

Journal of dairy science·2026
Same author

A respirometry system designed for small ruminants.

JDS communications·2025
Same author

Macromineral requirements for maintenance, body weight gain, and pregnancy of dairy cows.

Journal of dairy science·2025
Same author

Adjuvant-driven antibody response to use cows as biofactories of anti-SARS-CoV-2 neutralizing antibodies in colostrum.

Journal of dairy science·2025
Same author

Heat stress affects milk yield, milk quality, and gene expression profiles in mammary cells of Girolando cows.

Journal of dairy science·2024
Same author

Effects of bulk tank milk, waste milk, and pasteurized waste milk on the nutrient utilization, gastrointestinal tract development, and antimicrobial resistance to Escherichia coli in preweaning dairy calves.

Journal of dairy science·2024
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

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

Decentralized ADMM for factorization-based Low-rank matrix estimation.

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

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

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

Q-learning based asynchronous Boolean control networks stabilization with data loss.

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

New results on prescribed-time synchronization of complex networks via intermittent control.

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

Variance-constrained multi-view ensemble broad network for imbalanced data.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces Self-Organizing Tree (S-TREE) models for efficient data representation and vector quantization. S-TREE algorithms offer competitive performance in data clustering and image compression, significantly reducing computation time compared to existing methods.

Area of Science:

  • Machine Learning
  • Data Compression
  • Pattern Recognition

Background:

  • Hierarchical data representation is crucial for efficient data analysis.
  • Existing tree-structured vector quantizers (TSVQ) can be computationally intensive.
  • Unsupervised learning offers a powerful approach for data modeling.

Purpose of the Study:

  • Introduce the Self-Organizing Tree (S-TREE) model family.
  • Develop novel algorithms (S-TREE1 and S-TREE2) for unsupervised hierarchical data representation and vector quantization.
  • Evaluate S-TREE performance against established methods like TSVQ and Generalized Lloyd Algorithm (GLA).

Main Methods:

  • Developed S-TREE1 with a new tree-building algorithm adaptable to various cost functions.
  • Developed S-TREE2 utilizing a novel double-path search procedure.

Related Experiment Videos

  • Applied S-TREE models to data clustering, Gauss-Markov source benchmarking, and image compression tasks.

    • Main Results:

    • S-TREE2 achieved image reconstruction quality comparable to GLA with less than 10% of the computation time.
    • Both S-TREE1 and S-TREE2 demonstrated favorable performance against standard TSVQ in codebook generation time and image reconstruction quality.
    • S-TREE models effectively perform data clustering and vector quantization.

    Conclusions:

    • S-TREE models provide an efficient and effective approach for unsupervised hierarchical data representation and vector quantization.
    • S-TREE algorithms offer significant computational advantages over existing methods, particularly for image compression.
    • The S-TREE family represents a promising advancement in unsupervised learning for data analysis and compression.