Title :
A fast online learning algorithm for recurrent neural networks
Author :
Sun, Guo-Zheng ; Chen, Hsing-Hen ; Le, Y.-C.
Author_Institution :
Maryland Univ., College Park, MD, USA
Abstract :
The authors present arguments for a fast online training algorithm for recurrent neural networks. They present an algorithm that would require O(N3) calculations to update the weights in one time step, which is faster than all other known online training algorithms. They formulate the derivations of this algorithm in a variational approach which has the advantage of providing a unified view of the various algorithms that were derived by a number of researchers from very different circumstances
Keywords :
computational complexity; learning systems; neural nets; variational techniques; O(N3) calculations; complexity; fast online learning algorithm; fast online training algorithm; recurrent neural networks; variational approach; Astronomy; Backpropagation algorithms; Computer networks; Laboratories; Neural networks; Neurons; Physics computing; Recurrent neural networks; Speech; Sun;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155305
