Title :
Forward perturbation algorithm for a general class of recurrent network
Author :
De Jesús, Orlando ; 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 forward perturbation algorithm for computing the gradient of the network error with respect to the weights of the network
Keywords :
gradient methods; perturbation techniques; recurrent neural nets; forward perturbation algorithm; layered digital dynamic network; network error gradient; recurrent network; Backpropagation algorithms; Computer architecture; Computer errors; Computer networks; Delay lines; Differential equations; Feedback loop; Neural networks; Neurofeedback; Output feedback;
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.2001.938784
