A Modular Neural Network Architecture with Approximation Capability and Its Applications

	This Article
	Subscribers, please Login Purchase article: $19 PDF IEEE Xplore Subscribers RSS feed
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan/Endnote
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Changlin Cai Articles by Zhongzhi Shi

Second IEEE International Conference on Cognitive Informatics (ICCI'03)

London, England

August 18-August 20

ISBN: 0-7695-1986-5

	ASCII Text	x
	Changlin Cai, Zhongzhi Shi, "A Modular Neural Network Architecture with Approximation Capability and Its Applications," Cognitive Informatics, IEEE International Conference on, pp. 60, Second IEEE International Conference on Cognitive Informatics (ICCI'03), 2003.

	BibTex	x
	@article{ 10.1109/COGINF.2003.1225954, author = {Changlin Cai and Zhongzhi Shi}, title = {A Modular Neural Network Architecture with Approximation Capability and Its Applications}, journal ={Cognitive Informatics, IEEE International Conference on}, volume = {0}, year = {2003}, isbn = {0-7695-1986-5}, pages = {60}, doi = {http://doi.ieeecomputersociety.org/10.1109/COGINF.2003.1225954}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Cognitive Informatics, IEEE International Conference on TI - A Modular Neural Network Architecture with Approximation Capability and Its Applications SN - 0-7695-1986-5 SP EP A1 - Changlin Cai, A1 - Zhongzhi Shi, PY - 2003 KW - null VL - 0 JA - Cognitive Informatics, IEEE International Conference on ER -

Changlin Cai, Chinese Academy of Science

Zhongzhi Shi, Chinese Academy of Science

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/COGINF.2003.1225954

In this paper a new modular architecture of neural networks is designed to show that any continuous function which defined on a compact set can be approximated by a multilayer perceptrons, when the output layer activation functions are linear, and the hidden layer activation function could be chosen in the conditions of no bounded and no sigmoid. An application in econometrics forecast is proposed and analyzed, where the new function models can be added to the system one by one, so the complex system can be formed easily.

Citation:

Changlin Cai, Zhongzhi Shi, "A Modular Neural Network Architecture with Approximation Capability and Its Applications," icci, pp.60, Second IEEE International Conference on Cognitive Informatics (ICCI'03), 2003

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.