Title :
Design of a perceptron-like algorithm based on system identification techniques
Author_Institution :
IRIDIA Lab., Univ. Libre de Bruxelles
fDate :
3/1/1995 12:00:00 AM
Abstract :
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
Keywords :
Lyapunov methods; pattern classification; perceptrons; stability; Lyapunov stability formalism; adjustment rule; deterministic process identification; pattern classification; perceptron-like algorithm; saturating nonlinearity; system identification techniques; Adaptive control; Algorithm design and analysis; Associative memory; Circuit synthesis; Dispersion; Hopfield neural networks; Network synthesis; Neural networks; Scattering; System identification;
Journal_Title :
Neural Networks, IEEE Transactions on
