Conventional single layer networks are limited by their inability to solve non-linear classification problems. A modified neuron activation function has, recently, been proposed to extend the classification capabilities of single layer networks to cover some non-linear problems [1]. This paper shows that the classification capabilities of a multi-layer network can also be improved by incorporation of the modified activation function, in that the required number of hidden layers and that of hidden neurons for a complex application can be reduced. A multi-layer network, designed to perform textured image segmentation in computer vision applications is used in preliminary experiments to demonstrate the effectiveness of the new activation function.
展开▼
