Title :
Backpropagation through time for a general class of recurrent network
Author :
De Jeses, O. ; Hagan, Martin T.
Author_Institution :
Sch. of Electr. & Comput. Eng., Oklahoma State Univ., Stillwater, OK, USA
Abstract :
This paper introduces a general class of dynamic network, the layered digital dynamic network. It then derives the backpropagation-through-time algorithm for computing the gradient of the network error with respect to the weights of the network
Keywords :
backpropagation; multilayer perceptrons; recurrent neural nets; backpropagation-through-time algorithm; layered digital dynamic network; network error gradient; network weights; recurrent neural network; Backpropagation algorithms; Computer architecture; Computer errors; Computer networks; Equations; Feedback loop; Neural networks; Neurofeedback; Output feedback; Perturbation methods;
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.2001.938786
