@inproceedings{cf29f27aaa7f43ceb464c22108809167,
title = "EPNet for chaotic time-series prediction",
abstract = "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. {\textcopyright} Springer-Verlag Berlin Heidelberg 1997.",
keywords = "Hide Node, Chaotic Time Series, Architectural Evolution, Weight Learning, Node Deletion",
author = "Xin YAO and Yong LIU",
year = "1997",
doi = "10.1007/bfb0028531",
language = "English",
isbn = "9783540633990",
series = "Lecture Notes in Computer Science",
publisher = "Springer Berlin Heidelberg",
pages = "146--156",
editor = "Xin YAO and Jong-Hwan KIM and Takeshi FURUHASHI",
booktitle = "Simulated Evolution and Learning First Asia-Pacific Conference, SEAL'96, Taejon, Korea, November 9-12, 1996. Selected Papers",
}