EPNet for chaotic time-series prediction

Xin YAO, Yong LIU

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

16 Citations (Scopus)


EPNet is an evolutionary system for automatic design of artificial neural networks (ANNs) [1, 2, 3]. Unlike most previous methods on evolving ANNs, EPNet puts its emphasis on evolving ANN'S behaviours rather than circuitry. The parsimony of evolved ANNs is encouraged by the sequential application of architectural mutations. In this paper, EP Net is applied to a couple of chaotic time-series prediction problems (i.e., the Mackey-Glass differential equation and the logistic map). The experimental results show that EPNet can produce very compact ANNs with good prediction ability in comparison with other algorithms. © Springer-Verlag Berlin Heidelberg 1997.
Original languageEnglish
Title of host publicationSimulated Evolution and Learning First Asia-Pacific Conference, SEAL'96, Taejon, Korea, November 9-12, 1996. Selected Papers
EditorsXin YAO, Jong-Hwan KIM, Takeshi FURUHASHI
PublisherSpringer Berlin Heidelberg
Number of pages11
ISBN (Electronic)9783540695387
ISBN (Print)9783540633990
Publication statusPublished - 1997
Externally publishedYes

Publication series

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


  • Hide Node
  • Chaotic Time Series
  • Architectural Evolution
  • Weight Learning
  • Node Deletion


Dive into the research topics of 'EPNet for chaotic time-series prediction'. Together they form a unique fingerprint.

Cite this