Applications and analysis of second order artificial neural networks

The authors investigate a two-layer artificial neural network which consists of one hidden layer of second-order neurons and an output layer of first-order neurons. The second-order neurons yield conic-surface types of decision regions such as ellipses and parabolas. A simulation example is presented. It is shown that such networks yield more flexibility than first-order networks. An analysis of the memory capacities of single-layer and two-layer networks is presented.<
>