Title :
A procedure for training recurrent networks
Author :
Phan, Manh C. ; Beale, Mark H. ; Hagan, Martin T.
Author_Institution :
Sch. of Electr. & Comput. Eng., Oklahoma State Univ., Stillwater, OK, USA
Abstract :
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.
Keywords :
learning (artificial intelligence); recurrent neural nets; Levenberg-Marquardt algorithm; batch training method; error surface; individual sequences gradients; physical systems; recurrent neural networks; spurious valleys; Adaptation models; Heuristic algorithms; Magnetic levitation; Neural networks; Prediction algorithms; Training; Training data;
Conference_Titel :
Neural Networks (IJCNN), The 2013 International Joint Conference on
Conference_Location :
Dallas, TX
Print_ISBN :
978-1-4673-6128-6
DOI :
10.1109/IJCNN.2013.6706994