Title :
A complex EKF-RTRL neural network
Author :
Coelho, Pedro Henrique Gouvêa
Author_Institution :
Dept. of Electron. & Telecommun., State Univ. of Rio de Janeiro, Brazil
Abstract :
The purpose of the paper is to use extended Kalman filter (EKF) techniques in the complex real time recurrent learning (RTRL) neural network in order to have faster convergence as an alternative to standard gradient methods, usually used in RTRL neural networks training which are known to be slow. This characteristic is desired in many engineering applications, particularly those which are carried out online
Keywords :
Kalman filters; convergence; learning (artificial intelligence); recurrent neural nets; complex real time recurrent learning neural network; convergence; extended Kalman filter techniques; neural net training; Adaptive equalizers; Convergence; Feedback loop; Gradient methods; Neural networks; Neurons; Nonlinear equations; Recurrent neural networks; State-space methods; Telecommunication standards;
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.2001.939003
