TY - JOUR
T1 - Convergence of BP Algorithm for Training MLP with Linear Output
AU -  H. M. Shao, W. Wu & W. B. Liu
JO - Numerical Mathematics, a Journal of Chinese Universities
VL - 3
SP - 193
EP - 202
PY - 2007
DA - 2007/08
SN - 16
DO - http://doi.org/
UR - https://global-sci.org/intro/article_detail/nm/8053.html
KW - 
AB - 
The capability of multilayer perceptrons (MLPs) for approximating
continuous functions with arbitrary accuracy has been demonstrated
in the past decades. Back propagation $($BP$)$ algorithm is the most
popular learning algorithm for training of MLPs. In this paper, a
simple iteration formula is used to select the learning rate for
each cycle of training procedure, and a convergence result is
presented for the BP algorithm for training  MLP with a hidden layer
and a linear output unit. The monotonicity of the error function is
also guaranteed during the training iteration.