Constructive and Pruning Methods for Neural Network Design

S
SBRN
2002
VII Brazilian Symposium on Neural Networks (SBRN'02)
Abstract - Constructive and Pruning Methods for Neural Network Design

	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
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Marcelo Azevedo Costa Articles by Antônio Pádua Braga Articles by Benjamin Rodrigues de Menezes

VII Brazilian Symposium on Neural Networks (SBRN'02)

Pernambuco, Brazil

November 11-November 14

ISBN: 0-7695-1709-9

	ASCII Text	x
	Marcelo Azevedo Costa, Antônio Pádua Braga, Benjamin Rodrigues de Menezes, "Constructive and Pruning Methods for Neural Network Design," Neural Networks, Brazilian Symposium on, pp. 49, VII Brazilian Symposium on Neural Networks (SBRN'02), 2002.

	BibTex	x
	@article{ 10.1109/SBRN.2002.1181434, author = {Marcelo Azevedo Costa and Antônio Pádua Braga and Benjamin Rodrigues de Menezes}, title = {Constructive and Pruning Methods for Neural Network Design}, journal ={Neural Networks, Brazilian Symposium on}, volume = {0}, year = {2002}, isbn = {0-7695-1709-9}, pages = {49}, doi = {http://doi.ieeecomputersociety.org/10.1109/SBRN.2002.1181434}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Neural Networks, Brazilian Symposium on TI - Constructive and Pruning Methods for Neural Network Design SN - 0-7695-1709-9 SP EP A1 - Marcelo Azevedo Costa, A1 - Antônio Pádua Braga, A1 - Benjamin Rodrigues de Menezes, PY - 2002 KW - null VL - 0 JA - Neural Networks, Brazilian Symposium on ER -

Marcelo Azevedo Costa, Federal University of Minas Gerais

Antônio Pádua Braga, Federal University of Minas Gerais

Benjamin Rodrigues de Menezes, Federal University of Minas Gerais

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/SBRN.2002.1181434

This paper presents methods to improve generalization of Multi-Layer Perceptron (MLP) by pruning the original topology without loss in performance. Topology information and validation sets are used. The results show that these techniques are able to choose a minimum network topology and to simplify trained networks.

Citation:

Marcelo Azevedo Costa, Antônio Pádua Braga, Benjamin Rodrigues de Menezes, "Constructive and Pruning Methods for Neural Network Design," sbrn, pp.49, VII Brazilian Symposium on Neural Networks (SBRN'02), 2002

Peer Review Notice | Give Us Feedback

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