• Citer

Design of a perceptron-like algorithm based on system identification techniques

par Saerens, Marco
Référence IEEE transactions on neural networks, 6, 2, page (504-506)
Publication Publié, 1995-03

Article révisé par les pairs

• Détails
• Contenu

Résumé :

In this letter, we develop a new adjustment rule for a perceptron with a saturating nonlinearity that ensures perfect classification when the input patterns are linearly separable. The proof is based on the Lyapunov stability formalism, is widely used in deterministic process identification, and is rather straightforward. It should therefore be of pedagogical interest.