Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
9653598 | Neurocomputing | 2005 | 20 Pages |
Abstract
In this paper, fully connected RTRL neural networks are studied. In order to learn dynamical behaviours of continuous time processes or to predict numerical time series, an autonomous learning algorithm has been developed. The originality of this method consists in the gradient-based adaptation of the learning rate and time parameter of neurons using a small perturbations method. Starting from zero initial conditions (neural states, rate of learning, time parameter and matrix of weights) the evolution is completely driven by the dynamic of the learning data. Stability issues are discussed, and several examples are investigated in order to compare the performances of the adaptive learning rate and time parameter algorithm with the constant parameters one.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Edouard Leclercq, Fabrice Druaux, Dimitri Lefebvre, Salem Zerkaoui,