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

Self-organizing mixture networks for probability density estimation.

H Yin1, N M Allinson

  • 1Department of Electrical Engineering and Electronics, University of Manchester Institute of Science and Technology, Manchester, M60 1QD, UK.

IEEE Transactions on Neural Networks
|February 5, 2008
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

Global Burden of Disease from Major Air Pollution Sources (GBD MAPS): A Global Approach.

Research report (Health Effects Institute)·2022
Same author

CircSUCO promotes proliferation and differentiation of chicken skeletal muscle satellite cells <i>via</i> sponging miR-15.

British poultry science·2022
Same author

First Measurement of the Z→μ^{+}μ^{-} Angular Coefficients in the Forward Region of pp Collisions at sqrt[s]=13  TeV.

Physical review letters·2022
Same author

Efficacy of low-dose of baricitinib in the treatment of patchy alopecia and sicca syndrome in an SLE patient.

Scandinavian journal of rheumatology·2022
Same author

Angular Analysis of D^{0}→π^{+}π^{-}μ^{+}μ^{-} and D^{0}→K^{+}K^{-}μ^{+}μ^{-} Decays and Search for CP Violation.

Physical review letters·2022
Same author

Tests of Lepton Universality Using B^{0}→K_{S}^{0}ℓ^{+}ℓ^{-} and B^{+}→K^{*+}ℓ^{+}ℓ^{-} Decays.

Physical review letters·2022
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

This study introduces a self-organizing mixture network (SOMN) for learning complex density functions. The novel network efficiently estimates density profiles and aids in pattern classification tasks.

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Statistical Modeling

Background:

  • Density functions are fundamental in statistical modeling and machine learning.
  • Existing methods for learning arbitrary density functions can be computationally intensive or lack generalization.
  • Self-organizing maps (SOMs) offer unsupervised learning but have limitations in modeling complex, non-homogeneous distributions.

Purpose of the Study:

  • To develop a novel Self-Organizing Mixture Network (SOMN) capable of learning arbitrary density functions.
  • To model density functions as mixtures of potentially non-homogeneous parametric distributions.
  • To enhance pattern classification and density profile estimation using a robust and efficient network architecture.

Main Methods:

  • The SOMN employs a two-layer structure inspired by Kohonen's Self-Organizing Map (SOM).

Related Experiment Videos

  • The network minimizes the Kullback-Leibler information metric using stochastic approximation.
  • Learning involves a maximum posterior probability-based winning mechanism and localized weight updates, with a second layer accumulating weighted node responses.

    • Main Results:

    • The SOMN demonstrates fast and robust convergence in learning density functions.
    • The network exhibits generalization ability, attributed to the relative entropy criterion.
    • Successful applications in density profile estimation and pattern classification were presented.

    Conclusions:

    • The Self-Organizing Mixture Network (SOMN) provides an effective framework for learning arbitrary and non-homogeneous density functions.
    • The network's simple structure and computational efficiency facilitate rapid and reliable convergence.
    • SOMN offers insights into the neighborhood function's role in SOMs and shows promise for various machine learning applications.