Jove
Visualize
Contact Us

Related Experiment Videos

Fast neural network ensemble learning via negative-correlation data correction.

Zeke S H Chan, Nik Kasabov

    IEEE Transactions on Neural Networks
    |December 14, 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

    Bayesian learning of sparse gene regulatory networks.

    Bio Systems·2007
    Same author

    A hybrid genetic algorithm and expectation maximization method for global gene trajectory clustering.

    Journal of bioinformatics and computational biology·2005
    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
    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

    A novel negative correlation (NC) learning method is introduced, offering easier implementation and reduced communication overhead compared to standard approaches. This new NC method also supports ensembles of diverse neural networks.

    Area of Science:

    • Machine Learning
    • Artificial Intelligence
    • Neural Networks

    Background:

    • Standard negative correlation (NC) learning methods often involve significant communication overhead.
    • Applying existing NC methods to ensembles of heterogeneous networks can be challenging.

    Purpose of the Study:

    • To propose a new, easily implementable negative correlation (NC) learning method.
    • To reduce communication overhead in NC learning.
    • To enhance the applicability of NC learning to heterogeneous network ensembles.

    Main Methods:

    • Development of a novel negative correlation (NC) learning algorithm.
    • Implementation of the proposed NC method for comparative analysis.
    • Evaluation of communication overhead and network applicability.

    Related Experiment Videos

    Main Results:

    • The proposed NC learning method demonstrates significantly reduced communication overhead compared to standard NC methods.
    • The new NC method is successfully applied to ensembles of heterogeneous networks.
    • Ease of implementation is a key advantage of the proposed method.

    Conclusions:

    • The new negative correlation (NC) learning method offers a practical and efficient alternative.
    • This advancement facilitates the use of NC learning in more complex and diverse network architectures.
    • The method addresses key limitations of existing NC learning techniques.