Self-growing neural network architecture using crisp and fuzzy entropy
Krzysztof J. Cios · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1992
The paper briefly describes the self-growing neural network algorithm, CID3, which makes decision trees equivalent to hidden layers of a neural network. The algorithm generates a feedforward architecture using crisp and fuzzy entropy measures. The results for a real-life recognition problem of distinguishing defects in a glass ribbon, and for a benchmark problem of telling two spirals apart are shown and discussed.