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

SMEM algorithm for mixture models.

N Ueda1, R Nakano, Z Ghahramani

  • 1NTT Communication Science Laboratories, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237 Japan.

Neural Computation
|September 8, 2000
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

Glove-TalkII--a neural-network interface which maps gestures to parallel formant speech synthesizer controls.

IEEE transactions on neural networks·2008
Same author

Reducing the dimensionality of data with neural networks.

Science (New York, N.Y.)·2006
Same author

Computation by neural networks.

Nature neuroscience·2000
Same author

Variational learning for switching state-space models.

Neural computation·2000
Same author

Metabolic suppression of platelet-type 12-lipoxygenase in human uterine cervix with invasive carcinoma.

International journal of cancer·1999
Same author

An acid amidase hydrolyzing anandamide as an endogenous ligand for cannabinoid receptors.

FEBS letters·1999
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

A new split-and-merge expectation-maximization (SMEM) algorithm addresses local maxima in finite mixture models. This method improves parameter estimation and model performance in applications like image compression and pattern recognition.

Area of Science:

  • Machine Learning
  • Statistical Modeling
  • Computational Statistics

Background:

  • Finite mixture models are widely used for data clustering and density estimation.
  • Parameter estimation in mixture models can be challenging due to the problem of local maxima.
  • Local maxima can lead to suboptimal model configurations, particularly with uneven component distributions.

Purpose of the Study:

  • To introduce a novel Split-and-Merge Expectation-Maximization (SMEM) algorithm.
  • To overcome the local maxima problem in parameter estimation for finite mixture models.
  • To enhance the performance and applicability of mixture models in complex data scenarios.

Main Methods:

  • The SMEM algorithm employs simultaneous split-and-merge operations to escape local maxima.

Related Experiment Videos

  • A new criterion is introduced for efficient selection of split-and-merge candidates.
  • The algorithm is applied to Gaussian mixtures and mixtures of factor analyzers.

    • Main Results:

    • The SMEM algorithm effectively improves the likelihood for both training and held-out test data.
    • Demonstrated effectiveness on synthetic and real-world datasets.
    • Successful application to image compression and pattern recognition tasks.

    Conclusions:

    • The proposed SMEM algorithm provides a robust solution to the local maxima problem in mixture model parameter estimation.
    • SMEM enhances model performance and likelihood across various mixture model types.
    • The algorithm shows practical utility in real-world applications such as image compression and pattern recognition.