DocumentCode
1748924
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
Volume
4
fYear
2001
fDate
2001
Firstpage
2626
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;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location
Washington, DC
ISSN
1098-7576
Print_ISBN
0-7803-7044-9
Type
conf
DOI
10.1109/IJCNN.2001.938784
Filename
938784
Link To Document