Nature-Inspired Neural Network Ensemble Learning

Yong LIU, Xin YAO, Yong LIU

Research output: Journal PublicationsJournal Article (refereed)peer-review

1 Citation (Scopus)


Learning and evolution are two fundamental forms of adaptation from nature. This paper presents a nature inspired neural network ensemble learning (EENCL), in which evolution is another fundamental form of adaptation in addition to learning. Learning in EENCL is conducted at the individual level based on negative correlation learning that encourages each individual neural network to learn differently. Evolution in EENCL is processed by evolutionary programming at the population level to evolve a population of diverse neural networks. One distinct feature of EENCL is its adaptability to a dynamic environment. In other words, EENCL can make neural network ensembles adapt to an environment as well as changes in the environment. The evolution and learning in EENCL make the adaptation of neural network ensembles to a dynamic environment much more effective and efficient. © 2008 by Walter de Gruyter GmbH & Co. All rights reserved.
Original languageEnglish
Pages (from-to)5-26
Number of pages22
JournalJournal of Intelligent Systems
Issue numberSupplement
Publication statusPublished - Jan 2008
Externally publishedYes


  • evolutionary learning
  • generalization
  • nature inspired learning
  • negative correlation learning
  • neural network ensemble
  • optimization


Dive into the research topics of 'Nature-Inspired Neural Network Ensemble Learning'. Together they form a unique fingerprint.

Cite this