loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
5th Brazilian Symposium on Neural Networks
Automatic Target Recognition using a Constructive Approach
Belo Horizonte, MG, Brazil
December 09-December 11
ISBN: 0-8186-8629-4
ASCII Text
x 
 
Ernesto Cuadros Vargas, Humberto Costa de Sousa, Andre de Carvalho, "Automatic Target Recognition using a Constructive Approach," Neural Networks, Brazilian Symposium on, pp. 112, 5th Brazilian Symposium on Neural Networks, 1998.
 
 
BibTex
x
 
@article{ 10.1109/SBRN.1998.731005,
author = {Ernesto Cuadros Vargas and Humberto Costa de Sousa and Andre de Carvalho},
title = {Automatic Target Recognition using a Constructive Approach},
journal ={Neural Networks, Brazilian Symposium on},
volume = {0},
year = {1998},
issn = {1522-4899},
pages = {112},
doi = {http://doi.ieeecomputersociety.org/10.1109/SBRN.1998.731005},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Neural Networks, Brazilian Symposium on
TI - Automatic Target Recognition using a Constructive Approach
SN - 1522-4899
SP
EP
A1 - Ernesto Cuadros Vargas,
A1 - Humberto Costa de Sousa,
A1 - Andre de Carvalho,
PY - 1998
VL - 0
JA - Neural Networks, Brazilian Symposium on
ER -
 
Ernesto Cuadros Vargas, Universty of Sao Paulo
Humberto Costa de Sousa, Universty of Sao Paulo
Andre de Carvalho, Universty of Sao Paulo
This paper presents the use of Constructive Neural Networks for Automatic Target Recognition. The work presented here is a contribution for the SAPRI project (System for Acquisition, Processing and Images Recognition) which is being developed for the Brazilian Navy. The objective of this paper is to investigate the behavior of Constructive Neural Networks in image recognition tasks, specially with images from the SAPRI project. Constructive Neural Networks differ from standard networks due to their ability to change their own number of elements by adding or removing units and connections. Three constructive algorithms are presented in this paper: Cascade Correlation, Tower and Pyramid.
Citation:
Ernesto Cuadros Vargas, Humberto Costa de Sousa, Andre de Carvalho, "Automatic Target Recognition using a Constructive Approach," sbrn, pp.112, 5th Brazilian Symposium on Neural Networks, 1998
Usage of this product signifies your acceptance of the Terms of Use.