A constructive algorithm for training cooperative neural network ensembles

  • Islam M
  • Yao X
  • Murase K
  • 39

    Readers

    Mendeley users who have this article in their library.
  • 212

    Citations

    Citations of this article.

Abstract

Presents a constructive algorithm for training cooperative neural-network ensembles (CNNEs). CNNE combines ensemble architecture design with cooperative training for individual neural networks (NNs) in ensembles. Unlike most previous studies on training ensembles, CNNE puts emphasis on both accuracy and diversity among individual NNs in an ensemble. In order to maintain accuracy among individual NNs, the number of hidden nodes in individual NNs are also determined by a constructive approach. Incremental training based on negative correlation is used in CNNE to train individual NNs for different numbers of training epochs. The use of negative correlation learning and different training epochs for training individual NNs reflect CNNEs emphasis on diversity among individual NNs in an ensemble. CNNE has been tested extensively on a number of benchmark problems in machine learning and neural networks, including Australian credit card assessment, breast cancer, diabetes, glass, heart disease, letter recognition, soybean, and Mackey-Glass time series prediction problems. The experimental results show that CNNE can produce NN ensembles with good generalization ability.

Author-supplied keywords

  • Constructive approach
  • Diversity
  • Generalization
  • Negative correlation learning
  • Neural-network (NN) ensemble design

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Authors

  • Md Monirul Islam

  • Xin Yao

  • Kazuyuki Murase

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free