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 4
Bayesian Training of Mixture Density Networks
Como, Italy
July 24-July 27
ISBN: 0-7695-0619-4
ASCII Text
x 
 
Lars U. Hjorth, Ian T. Nabney, "Bayesian Training of Mixture Density Networks," Neural Networks, IEEE - INNS - ENNS International Joint Conference on, vol. 4, pp. 4455, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 4, 2000.
 
 
BibTex
x
 
@article{ 10.1109/IJCNN.2000.860813,
author = {Lars U. Hjorth and Ian T. Nabney},
title = {Bayesian Training of Mixture Density Networks},
journal ={Neural Networks, IEEE - INNS - ENNS International Joint Conference on},
volume = {4},
year = {2000},
issn = {1098-7576},
pages = {4455},
doi = {http://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.860813},
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 - Bayesian Training of Mixture Density Networks
SN - 1098-7576
SP
EP
A1 - Lars U. Hjorth,
A1 - Ian T. Nabney,
PY - 2000
VL - 4
JA - Neural Networks, IEEE - INNS - ENNS International Joint Conference on
ER -
 
Lars U. Hjorth, Aston University
Ian T. Nabney, Aston University
Mixture Density Networks (MDNs) are a well-established method for modeling the conditional probability density, which is useful for complex multi-valued functions where regression methods (such as MLPs) fail. In this paper, we extend earlier research of a regularization method for a special case of MDNs to the general case using evidence based regularization and we show how the Hessian of the MDN error function can be evaluated using R -propagation. The method is tested on two data sets and compared with early stopping.
Citation:
Lars U. Hjorth, Ian T. Nabney, "Bayesian Training of Mixture Density Networks," ijcnn, vol. 4, pp.4455, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 4, 2000
Usage of this product signifies your acceptance of the Terms of Use.