TY - JOUR
T1 - Convergence of Gradient Method with Momentum for Back-Propagation Neural Networks
JO - Journal of Computational Mathematics
VL - 4
SP - 613
EP - 623
PY - 2008
DA - 2008/08
SN - 26
DO - http://doi.org/
UR - https://global-sci.org/intro/article_detail/jcm/8645.html
KW - Back-propagation (BP) neural networks, Gradient method, Momentum, Convergence.
AB - <p style="text-align: justify;">In this work, a gradient method with momentum for BP neural networks is considered. The momentum coefficient is chosen in an adaptive manner to accelerate and stabilize the learning procedure of the network weights. Corresponding convergence results are proved.</p>