DESIGN OF A PERCEPTRON-LIKE ALGORITHM-BASED ON SYSTEM-IDENTIFICATION TECHNIQUES

Authors
SAERENS M
Citation
M. Saerens, DESIGN OF A PERCEPTRON-LIKE ALGORITHM-BASED ON SYSTEM-IDENTIFICATION TECHNIQUES, IEEE transactions on neural networks, 6(2), 1995, pp. 504-506
Citations number
19
Categorie Soggetti
Computer Application, Chemistry & Engineering","Engineering, Eletrical & Electronic","Computer Science Artificial Intelligence","Computer Science Hardware & Architecture","Computer Science Theory & Methods
Journal title
IEEE transactions on neural networks → ACNP
ISSN journal
10459227
Volume
6
Issue
2
Year of publication
1995
Pages
504 - 506
Database
ISI
SICI code
1045-9227(1995)6:2<504:DOAPAO>2.0.ZU;2-T
Abstract
In this letter, we develop a new adjustment rule for a perceptron with a saturating nonlinearity that ensures perfect classification when th e input patterns are linearly separable. The proof is based on the Lya punov stability formalism, is widely used in deterministic process ide ntification, and is rather straightforward. It should therefore be of pedagogical interest.