×

Convergence of the gradient method with momentum for back-propagation neural networks. (English) Zbl 1174.68519

Summary: 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.

MSC:

68T05 Learning and adaptive systems in artificial intelligence
PDF BibTeX XML Cite