A new algorithm is proposed for improving the convergence of backpropagtion networks. This algorithm is obtained by combining the conjugate gradient method and the Kalman filter algorithm. Simulation results show that the proposed algorithm can perform satisfactorily in all cases considered.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Songyot SUREERATTANAN, Huynh Ngoc PHIEN, "New Developments on Backpropagation Network Training" in IEICE TRANSACTIONS on Fundamentals,
vol. E83-A, no. 6, pp. 1032-1039, June 2000, doi: .
Abstract: A new algorithm is proposed for improving the convergence of backpropagtion networks. This algorithm is obtained by combining the conjugate gradient method and the Kalman filter algorithm. Simulation results show that the proposed algorithm can perform satisfactorily in all cases considered.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e83-a_6_1032/_p
Copy
@ARTICLE{e83-a_6_1032,
author={Songyot SUREERATTANAN, Huynh Ngoc PHIEN, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={New Developments on Backpropagation Network Training},
year={2000},
volume={E83-A},
number={6},
pages={1032-1039},
abstract={A new algorithm is proposed for improving the convergence of backpropagtion networks. This algorithm is obtained by combining the conjugate gradient method and the Kalman filter algorithm. Simulation results show that the proposed algorithm can perform satisfactorily in all cases considered.},
keywords={},
doi={},
ISSN={},
month={June},}
Copy
TY - JOUR
TI - New Developments on Backpropagation Network Training
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1032
EP - 1039
AU - Songyot SUREERATTANAN
AU - Huynh Ngoc PHIEN
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E83-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 2000
AB - A new algorithm is proposed for improving the convergence of backpropagtion networks. This algorithm is obtained by combining the conjugate gradient method and the Kalman filter algorithm. Simulation results show that the proposed algorithm can perform satisfactorily in all cases considered.
ER -