Time series prediction by using negatively correlated neural networks

Yong LIU, Xin YAO

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

5 Citations (Scopus)

Abstract

Negatively correlated neural networks (NCNNs) have been proposed to design neural network (NN) ensembles [1]. The idea of NC-NNs is to encourage different individual NNs in the ensemble to learn different parts or aspects of a training data so that the ensemble can learn the whole training data better. The cooperation and specialisation among different individual NNs are considered during the individual NN design. This provides an opportunity for different NNs to interact with each other and to specialise. In this paper, NCNNs are applied to two time series prediction problems (i.e., the Mackey-Glass differential equation and the chlorophyll-a prediction in Lake Kasumigaura). The experimental results show that NCNNs can produce NN ensembles with good generalisation ability. © Springer-Verlag Berlin Heidelberg 1999.
Original languageEnglish
Title of host publicationSimulated Evolution and Learning : Second Asia-Pacific Conference on Simulated Evolution and Learning, SEAL'98, Canberra, Australia, November 24-27, 1998 Selected Papers
EditorsBob MCKAY, Xin YAO, Charles S. NEWTON, Jong-Hwan KIM, Takeshi FURUHASHI
PublisherSpringer Berlin Heidelberg
Pages333-340
Number of pages8
ISBN (Electronic)9783540488736
ISBN (Print)9783540659075
DOIs
Publication statusPublished - 1999
Externally publishedYes
Event2nd Asia-Pacific Conference on Simulated Evolution and Learning, SEAL 1998 - Canberra, Australia
Duration: 24 Nov 199827 Nov 1998

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin, Heidelberg
Volume1585
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference2nd Asia-Pacific Conference on Simulated Evolution and Learning, SEAL 1998
Country/TerritoryAustralia
CityCanberra
Period24/11/9827/11/98

Keywords

  • Time Series Prediction
  • Individual Network
  • Neural Network Ensemble
  • Good Generalisation Ability
  • Negative Correlation Learning

Fingerprint

Dive into the research topics of 'Time series prediction by using negatively correlated neural networks'. Together they form a unique fingerprint.

Cite this