loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 5
An Incremental Growing Neural Network and its Application to Robot Control
Como, Italy
July 24-July 27
ISBN: 0-7695-0619-4
ASCII Text
x 
 
A. Carlevarino, R. Martinotti, G. Metta, G. Sandini, "An Incremental Growing Neural Network and its Application to Robot Control," Neural Networks, IEEE - INNS - ENNS International Joint Conference on, vol. 5, pp. 5323, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 5, 2000.
 
 
BibTex
x
 
@article{ 10.1109/IJCNN.2000.861486,
author = {A. Carlevarino and R. Martinotti and G. Metta and G. Sandini},
title = {An Incremental Growing Neural Network and its Application to Robot Control},
journal ={Neural Networks, IEEE - INNS - ENNS International Joint Conference on},
volume = {5},
year = {2000},
issn = {1098-7576},
pages = {5323},
doi = {http://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.861486},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Neural Networks, IEEE - INNS - ENNS International Joint Conference on
TI - An Incremental Growing Neural Network and its Application to Robot Control
SN - 1098-7576
SP
EP
A1 - A. Carlevarino,
A1 - R. Martinotti,
A1 - G. Metta,
A1 - G. Sandini,
PY - 2000
VL - 5
JA - Neural Networks, IEEE - INNS - ENNS International Joint Conference on
ER -
 
A. Carlevarino, University of Genova
R. Martinotti, University of Genova
G. Metta, University of Genova
G. Sandini, University of Genova
This paper describes a novel network model, which is able to control its growth based on the approximation requests. Two classes of self-tuning neural models are considered; namely, Growing Neural Gas (GNG) and SoftMax function networks. We combined the two models: hence, the name GNG-Soft networks. The resulting model is characterized by the effectiveness of the GNG in distributing the units within the input space and the approximation properties of SoftMax functions. We devised a method to estimate the approximation error in an incremental fashion. This measure has been used to tune the network growth rate. Results showing the performance of the network in a real-world robotic experiment are reported.
Citation:
A. Carlevarino, R. Martinotti, G. Metta, G. Sandini, "An Incremental Growing Neural Network and its Application to Robot Control," ijcnn, vol. 5, pp.5323, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 5, 2000
Usage of this product signifies your acceptance of the Terms of Use.