Korbicz, Józef - red. ; Uciński, Dariusz - red.
The UD RLS algorithm for training feedforward neural networks
Group publication title:
Subject and Keywords:
neural networks ; learning algorithms ; recursive least squares method ; UD factorization
A new algorithm for training feedforward multilayer neural networks is proposed. It is based on recursive least squares procedures and U-D factorization, which is a well-known technique in filter theory. It will be shown that due to the U-D factorization method, our algorithm requires fewer computations than the classical RLS applied to feedforward multilayer neural network training.
Zielona Góra: Uniwersytet Zielonogórski
AMCS, volume 15, number 1 (2005) ; click here to follow the link