Arbitrary classification by a novel generating-shrinking algorithm
Yan Qiu Chen, David Thomas, Mark S. Nixon · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1994
A novel algorithm is proposed in this paper, which builds and then shrinks a three-layer feed- forward neural network to achieve arbitrary classification in the n-dimensional Euclidean space. The algorithm offers guaranteed convergence and a 100% correct classification rate on training patterns, as well as an explicit generalization rule for predicting how a trained network generalizes to patterns that did not appear in training. Moreover, this generalization rule is continuously adjustable from an equal-angle measure to an equal-distance measure via a single reference number to allow adaptation of performance for different requirements.