A procedure for training recurrent networks
Manh Cong Phan, Mark Beale, Martin Hagan · 2013
In this paper, we introduce a new procedure for efficient training of recurrent neural networks. The new procedure uses a batch training method based on a modified version of the Levenberg-Marquardt algorithm. The information of gradients of individual sequences is used to mitigate the effect of spurious valleys in the error surface of recurrent networks. The method is tested on the modeling and control of several physical systems.