Capacity and generalization measurement of feedforward neural networks
Feng Yuankun · Journal of Tsinghua University(Science and Technology) · 1999
The complexity of a given problem and the capacity and the ability in the sense of statistics of artificial neural networks (ANN) are the key factors that influence the generalization of ANN. By investigating the capacity and the ability in the sense of statistics of feedforward neural networks (FNN), A measurement of capacity and generalization of FNN, which can be used to estimate the proper number of FNN hidden nodes is defined. This method is applicable to functional approximation and classification problems.