A novel class of neural networks with quadratic junctions

機構典藏 > College of Engineering > Graduate Institute & Department of Electrical Engineering > Proceeding > Item 987654321/70269

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/70269

Title:	A novel class of neural networks with quadratic junctions
Authors:	DeClaris, Nicholas;Su, Mu-chun
Contributors:	淡江大學電機工程學系
Date:	1991-10
Issue Date:	2011-10-23 21:07:04 (UTC+8)
Publisher:	IEEE
Abstract:	The authors discuss the architecture and training properties of a multilayer feedforward neural network class that uses quadratic junctions in a neural architecture that uses effectively the backpropagation learning algorithm given by P.J. Werbos (1989). Both the architecture of the quadratic junctions and the backpropagation were adopted so as to endow the networks with appealing training properties (under supervision) and acceptable generalizations. Complexity and learning aspects of this class are examined and compared with traditional networks that use linear junctions.
Relation:	Proceedings of the IEEE international conferences on systems, man, and cybernetics, v.3,p.p1557 - 1562
DOI:	10.1109/ICSMC.1991.169910
Appears in Collections:	[Graduate Institute & Department of Electrical Engineering] Proceeding

Files in This Item:

There are no files associated with this item.