Design of a perceptron-like algorithm based on system identification techniques
M. Saeren · IEEE Transactions on Neural Networks · 1995
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.