Statistical method of pruning neural networks
Jessica Lo · 2003
A statistical method of pruning multilayer perceptrons is proposed which is expected to involve less computation than does "optimal brain surgeon". The statistical method iteratively performs the steps of estimating the error covariance of the weights, evaluating the z-statistics for the weights, pruning the weights selected by hypothesis testing, and re-training the neural network. An interesting relationship between the statistical method and "optimal brain surgeon" is discussed. The relationship provides some insight into these two methods.