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

A constructive algorithm for training cooperative neural network ensembles.

Md M Islam1, Xin Yao, K Murase

  • 1Dept. of Human and Artificial Intelligence Syst., Fukui Univ., Japan.

IEEE Transactions on Neural Networks
|February 2, 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

An overview of microscale indentation fatigue: Composites, thin films, coatings, and ceramics.

Micron (Oxford, England : 1993)·2021
Same author

Association of vitamin D status with incidence of enterotoxigenic, enteropathogenic and enteroaggregative Escherichia coli diarrhoea in children of urban Bangladesh.

Tropical medicine & international health : TM & IH·2016
Same author

Mouth breathing, another risk factor for asthma: the Nagahama Study.

Allergy·2016
Same author

The anoikis effector Bit1 displays tumor suppressive function in lung cancer cells.

PloS one·2014
Same author

Efficient identification of mutated cancer antigens recognized by T cells associated with durable tumor regressions.

Clinical cancer research : an official journal of the American Association for Cancer Research·2014
Same author

Overexpression of HP1γ is associated with poor prognosis in non-small cell lung cancer cell through promoting cell survival.

Tumour biology : the journal of the International Society for Oncodevelopmental Biology and Medicine·2014
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 constructive algorithm for training cooperative neural-network ensembles (CNNEs), focusing on both accuracy and diversity. CNNEs demonstrate strong generalization ability across various benchmark machine learning problems.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Ensemble methods in machine learning aim to improve predictive performance by combining multiple models.
  • Traditional ensemble training often prioritizes accuracy, potentially sacrificing diversity among individual models.
  • Cooperative Neural-Network Ensembles (CNNEs) address the need for both accuracy and diversity in ensemble training.

Purpose of the Study:

  • To present a novel constructive algorithm for training cooperative neural-network ensembles (CNNEs).
  • To emphasize both the accuracy and diversity of individual neural networks (NNs) within an ensemble.
  • To determine the optimal number of hidden nodes for individual NNs using a constructive approach.

Main Methods:

  • CNNE combines ensemble architecture design with cooperative training for individual NNs.

Related Experiment Videos

  • A constructive approach is used to determine the number of hidden nodes in individual NNs, maintaining accuracy.
  • Incremental training based on negative correlation learning and varied training epochs are employed to enhance diversity among NNs.

    • Main Results:

    • CNNE was extensively tested on benchmark datasets including credit card assessment, breast cancer, diabetes, glass, heart disease, letter recognition, soybean, and Mackey-Glass time series.
    • Experimental results indicate that CNNE effectively produces NN ensembles with good generalization capabilities.
    • The approach successfully balances accuracy and diversity in the trained neural network ensembles.

    Conclusions:

    • CNNE offers an effective constructive algorithm for training cooperative neural network ensembles.
    • The method enhances ensemble generalization ability by focusing on both individual network accuracy and inter-network diversity.
    • CNNE provides a valuable framework for developing high-performing neural network ensembles in machine learning.