DocumentCode :
3282011
Title :
The Growing Self-Organizing Surface Map: Improvements
Author :
DalleMole, Vilson L. ; Araujo, Aluizio F. R.
fYear :
2008
fDate :
26-30 Oct. 2008
Firstpage :
183
Lastpage :
188
Abstract :
The growing self organizing surface map (GSOSM) is a novel map model that learns a 2D surface immersed in a 3D space. The GSOSM model introduces a novel connection learning rule called CCHL. In this paper we present an overview of GSOSM model and its connection learning rule CCHL. The GSOSM dynamic is analyzed and changes are proposed to improve the algorithm performance and time run. The results of the proposed improvements are depicted and discussed.
Keywords :
learning (artificial intelligence); self-organising feature maps; algorithm performance; connection learning rule; growing self-organizing surface map; Algorithm design and analysis; Clouds; Least squares approximation; Neural networks; Organizing; Performance analysis; Shape; Signal processing algorithms; Surface fitting; Surface reconstruction; GSOSM; SOM; Surface Reconstruction;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2008. SBRN '08. 10th Brazilian Symposium on
Conference_Location :
Salvador
ISSN :
1522-4899
Print_ISBN :
978-1-4244-3219-6
Electronic_ISBN :
1522-4899
Type :
conf
DOI :
10.1109/SBRN.2008.16
Filename :
4665913
Link To Document :
بازگشت