Title :
Analysis of recurrent network training and suggestions for improvements
Author :
De Jesús, Orlando ; Horn, Jason M. ; Hagan, Martin T.
Author_Institution :
Sch. of Electr. & Comput. Eng., Oklahoma State Univ., Stillwater, OK, USA
Abstract :
This paper describes some of the difficulties in training recurrent neural network, provides explanations for why these difficulties occur and explains how they can be mitigated
Keywords :
learning (artificial intelligence); recurrent neural nets; dynamic system control; dynamic system identification; recurrent neural network training; Annealing; Computer networks; Control systems; Convergence; Error analysis; Error correction; Interpolation; Neural networks; Recurrent neural networks; Shape;
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7044-9
DOI :
10.1109/IJCNN.2001.938785
