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 1
Technique of Learning Rate Estimation for Efficient Training of MLP
Como, Italy
July 24-July 27
ISBN: 0-7695-0619-4
ASCII Text
x 
 
Vladimir Golovko, Yury Savitsky, A. Sachenko, T. Laopoulo, L. Grandinetti, "Technique of Learning Rate Estimation for Efficient Training of MLP," Neural Networks, IEEE - INNS - ENNS International Joint Conference on, vol. 1, pp. 1323, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 1, 2000.
 
 
BibTex
x
 
@article{ 10.1109/IJCNN.2000.857856,
author = {Vladimir Golovko and Yury Savitsky and A. Sachenko and T. Laopoulo and L. Grandinetti},
title = {Technique of Learning Rate Estimation for Efficient Training of MLP},
journal ={Neural Networks, IEEE - INNS - ENNS International Joint Conference on},
volume = {1},
year = {2000},
issn = {1098-7576},
pages = {1323},
doi = {http://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.857856},
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 - Technique of Learning Rate Estimation for Efficient Training of MLP
SN - 1098-7576
SP
EP
A1 - Vladimir Golovko,
A1 - Yury Savitsky,
A1 - A. Sachenko,
A1 - T. Laopoulo,
A1 - L. Grandinetti,
PY - 2000
VL - 1
JA - Neural Networks, IEEE - INNS - ENNS International Joint Conference on
ER -
 
Vladimir Golovko, Brest Polytechnic Institute
Yury Savitsky, Brest Polytechnic Institute
A. Sachenko, Aristotle University of Thessaloniki
T. Laopoulo, Ternopil Academy of National Economy
L. Grandinetti, University of Calabria
A new computational technique for training of multilayer feed-forward neural networks with sigmoid activation function of the units is proposed. The proposed algorithm consists two phases. The first phase is an adaptive training step calculation, which implements the steepest descent method in the weight space. The second phase is estimation of calculated training step rate, which provide reach a state of activity of the units on the each training iteration. The simulation results are provided for the test example to demonstrate the efficiency of the proposed method, which solves the problem of training step choice in multilayer perceptions.
Citation:
Vladimir Golovko, Yury Savitsky, A. Sachenko, T. Laopoulo, L. Grandinetti, "Technique of Learning Rate Estimation for Efficient Training of MLP," ijcnn, vol. 1, pp.1323, 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.