1. The Vapnik-Chervonenkis dimension: Information versus complexity in learning;Abu Mostafa;Neural Computation,1989
2. Orthogonal transforms for digital signal processing;Ahmed,1975
3. Constructing hidden units using examples and queries;Baum,1991
4. Supervised learning of probability distributions by neural networks;Baum,1987
5. Learning in higher-order ‘artificial dendritic trees.’;Bell,1990