loading...
Training Feedforward Neural Networks with the Dogleg Method and BFGS Hessian Updates
Como, Italy July 24-July 27
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.857827IEEE-INNS-ENNS International Joint Co ...
 This Article 
 
Buy PURCHASE ARTICLE: $19
PDF
HTML
Buy IEEE Xplore Subscribers
 
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
ASCII Text
x 
 
S.J. Perantonis, N. Ampazis, S. Spirou, "Training Feedforward Neural Networks with the Dogleg Method and BFGS Hessian Updates," Neural Networks, IEEE - INNS - ENNS International Joint Conference on, vol. 1, pp. 1138, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 1, 2000.
 
 
BibTex
x
 
@article{ 10.1109/IJCNN.2000.857827,
author = {S.J. Perantonis and N. Ampazis and S. Spirou},
title = {Training Feedforward Neural Networks with the Dogleg Method and BFGS Hessian Updates},
journal ={Neural Networks, IEEE - INNS - ENNS International Joint Conference on},
volume = {1},
year = {2000},
issn = {1098-7576},
pages = {1138},
doi = {http://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.857827},
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 - Training Feedforward Neural Networks with the Dogleg Method and BFGS Hessian Updates
SN - 1098-7576
SP
EP
A1 - S.J. Perantonis,
A1 - N. Ampazis,
A1 - S. Spirou,
PY - 2000
VL - 1
JA - Neural Networks, IEEE - INNS - ENNS International Joint Conference on
ER -
 
S.J. Perantonis, National Center for Scientific Research\DEMOKRITOS
N. Ampazis, National Center for Scientific Research\DEMOKRITOS
S. Spirou, King's College London
In this paper, we introduce an advanced optimization algorithm for training feedforward neural networks. The algorithm combines the BFGS Hessian update formula with a special case of trust region techniques, called the Dogleg method, as an altenative technique to line search methods. Simulations regarding classification and function approximation problems are presented which reveal a clear improvement both in convergence and success rates over standard BFGS implementations.
Citation:
S.J. Perantonis, N. Ampazis, S. Spirou, "Training Feedforward Neural Networks with the Dogleg Method and BFGS Hessian Updates," ijcnn, vol. 1, pp.1138, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 1, 2000
Usage of this product signifies your acceptance of the Terms of Use.