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

Mixture modeling with pairwise, instance-level class constraints.

Qi Zhao1, David J Miller

  • 1Department of Electrical Engineering, Penn State University, University Park, PA 16802, USA. qzz100@psu.edu

Neural Computation
|September 15, 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

Sperm-female interactions in the pig oviduct, a key for insemination success?

The Journal of reproduction and development·2026
Same author

Designed Water Capture in Terpene Synthase Catalysis.

Chembiochem : a European journal of chemical biology·2026
Same author

Microbial Metabolism and Disease Virulence Changes Across Day and Night in Coral Black Band Disease Lesions.

Environmental microbiology·2026
Same author

Major transitions in early coral development: novel insights enabled by visualisation of a comprehensive transcriptomic dataset for Acropora millepora.

BMC biology·2026
Same author

U.S. Leadership in Food Safety: A Blueprint for Global Food Security through Pesticide Science.

Journal of agricultural and food chemistry·2025
Same author

Bridging the Divide: U.S. Leadership in Pesticide Policy for Global Food Security and Trade.

Journal of agricultural and food chemistry·2025
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

This study introduces a novel semisupervised clustering method that accurately estimates the number of classes and components, even when the number of classes is unknown. It overcomes limitations of prior methods by allowing multiple components per class and discovering new classes.

Area of Science:

  • Machine Learning
  • Data Mining
  • Computational Statistics

Background:

  • Semisupervised clustering integrates instance-level supervision with unsupervised learning to identify data groups.
  • Existing methods often assume a known number of classes and a one-cluster-per-class structure, which can be limiting.
  • The presence of constraints can be detrimental when these assumptions are violated, hindering the discovery of true data groups.

Purpose of the Study:

  • To develop a flexible semisupervised clustering and mixture modeling approach.
  • To address the challenge of unknown class numbers and the invalidity of the one-cluster-per-class assumption.
  • To enable the discovery of new classes from constrained and unconstrained data components.

Main Methods:

  • The proposed method allows multiple mixture components to be allocated to individual classes.

Related Experiment Videos

  • It simultaneously estimates both the number of mixture components and the number of classes.
  • Unconstrained components are treated as potential new classes, facilitating new class discovery.

    • Main Results:

    • The method accurately estimates the number of classes in both synthetic and real-world datasets.
    • Performance is favorably compared against established methods, including the approach by Shental et al. (2003).
    • The approach demonstrates robustness in scenarios where traditional assumptions do not hold.

    Conclusions:

    • The developed semisupervised clustering technique offers a more robust and flexible alternative to existing methods.
    • It effectively handles unknown class numbers and relaxes the strict one-cluster-per-class assumption.
    • The method shows promise for accurate group discovery and new class identification in complex datasets.