A modified neuron activation function which enables single layer perceptrons to solve some linearly inseparable problems

It is well known that the representational ability of early neural network paradigms, notably, perception Adaline and Madaline, is limited to only linearly separable classification problems. This has been well documented in Minsky and Papert´s book (1969). In this paper, a modified neuron activation function is proposed to extend the classification capability of individual neurons to cover a limited range of nonlinear classification problems. A training algorithm for single layer networks using the modified function is developed and its performance described.