Title :
A stable learning algorithm for recurrent neural networks
Author :
Parthasarathy, Guturu ; Pareek, Harish ; Ananthraj, P.
Author_Institution :
Dept. of Electron. & Electr. Commun. Eng., Indian Inst. of Technol., Kharagpur, India
Abstract :
The authors used the Liapunov approach to derive a new set of sufficient conditions that explain the stability of feedforward networks. A simplification of these conditions results in a new recurrent backpropagation algorithm. This algorithm preserves the local updating characteristic of the original algorithm but is, at the same time, found to be quite effective even for problems which offered resistance to solution by L. B. Almeida´s (1987) approach
Keywords :
Lyapunov methods; learning systems; neural nets; stability; Liapunov approach; feedforward networks; recurrent backpropagation algorithm; recurrent neural networks; stable learning algorithm; Annealing; Artificial intelligence; Backpropagation algorithms; Iterative algorithms; Multi-layer neural network; Multilayer perceptrons; Neural networks; Pattern classification; Recurrent neural networks; Stability criteria;
Conference_Titel :
Tools for Artificial Intelligence, 1991. TAI '91., Third International Conference on
Conference_Location :
San Jose, CA
Print_ISBN :
0-8186-2300-4
DOI :
10.1109/TAI.1991.167094
