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

Differential log likelihood for evaluating and learning gaussian mixtures.

Marc M Van Hulle1

  • 1K. U. Leuven, Laboratorium voor Neuro- en Psychofysiologie, B-3000 Leuven, Belgium. marc@neuro.kuleuven.ac.be

Neural Computation
|December 28, 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

Correction: EEG-based classification of alzheimer's disease and frontotemporal dementia using functional connectivity.

Scientific reports·2026
Same author

The electrophysiological basis of resting-state fMRI hyperconnectivity in early Alzheimer's disease.

Alzheimer's research & therapy·2026
Same author

A Cross-Subject Band-Power Complexity Metric for Detecting Mental Fatigue Through EEG.

Brain sciences·2026
Same author

Word classification across speech modes from low-density electrocorticography signals.

Journal of neural engineering·2026
Same author

EEG-based classification of alzheimer's disease and frontotemporal dementia using functional connectivity.

Scientific reports·2026
Same author

Early aperiodic EEG changes in preclinical and prodromal Alzheimer's disease.

Alzheimer's research & therapy·2026
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

We present differential log likelihood, a new unbiased metric for evaluating Gaussian mixture density estimation. This metric helps optimize Gaussian mixtures and introduces a novel learning strategy for improved performance on real-world data.

Area of Science:

  • Machine Learning
  • Statistical Modeling
  • Data Science

Background:

  • Density estimation is crucial for understanding data distributions.
  • Gaussian mixtures are a common tool for density estimation.
  • Existing metrics may lack unbiasedness, affecting model evaluation.

Purpose of the Study:

  • Introduce a novel unbiased metric, differential log likelihood, for Gaussian mixture density estimation quality.
  • Apply the new metric to determine optimal parameters (smoothness, number of kernels) for Gaussian mixtures.
  • Propose and evaluate a new learning strategy for Gaussian mixture density estimation.

Main Methods:

  • Developed the differential log likelihood metric.
  • Utilized the metric to find optimal smoothness and kernel count in Gaussian mixtures.

Related Experiment Videos

  • Implemented and compared a new learning strategy against log likelihood maximization.

    • Main Results:

    • The differential log likelihood provides an unbiased assessment of density estimation quality.
    • Optimal smoothness and kernel numbers were determined using the new metric.
    • The proposed learning strategy demonstrated competitive or superior performance compared to log likelihood maximization across diverse datasets.

    Conclusions:

    • Differential log likelihood is a valuable tool for unbiased Gaussian mixture evaluation.
    • The study provides a method for optimizing Gaussian mixture models.
    • The novel learning strategy offers an effective alternative for density estimation.