RECURRENT NEURAL NETWORKS - A CONSTRUCTIVE ALGORITHM, AND ITS PROPERTIES

Authors
TSOI AC TAN SH
Citation
Ac. Tsoi et Sh. Tan, RECURRENT NEURAL NETWORKS - A CONSTRUCTIVE ALGORITHM, AND ITS PROPERTIES, Neurocomputing, 15(3-4), 1997, pp. 309-326
Citations number
18
Categorie Soggetti
Computer Sciences, Special Topics","Computer Science Artificial Intelligence",Neurosciences
Journal title
Neurocomputing → ACNP
ISSN journal
09252312
Volume
15
Issue
3-4
Year of publication
1997
Pages
309 - 326
Database
ISI
SICI code
0925-2312(1997)15:3-4<309:RNN-AC>2.0.ZU;2-M
Abstract
In this paper, a constructive algorithm for a general recurrent neural network is proposed based on radial basis functions. It is shown that this algorithm is globally convergent. In addition, we will present t wo examples to illustrate the proposed method.