Generating-shrinking algorithm for learning arbitrary classification

This paper proposes a novel generating-shrinking algorithm, which builds and then shrinks a three-layer feed-forward neural network to achieve arbitrary classification in n-dimensional Euclidean space. The algorithm offers guaranteed convergence to a 100% correct classification rate on training patterns. Decision regions resulting from the algorithm are analytically described, so the generalisation behaviour of the trained network is analytically known. By altering the value of a reference number, the trained neural classifier can achieve scale-invariant generalisation as well as equal-distance generalisation to accommodate different requirements.