Variance analysis of sensitivity information for pruning multilayer feedforward neural networks
Andries Petrus Engelbrecht, L. Royal Fletcher, Ian Cloete · 2003
This paper presents an algorithm for pruning feedforward neural network architectures using sensitivity analysis. Sensitivity Analysis is used to quantify the relevance of input and hidden units. A new statistical pruning heuristic is proposed, based on the variance analysis, to decide which units to prune. Results are presented to show that the pruning algorithm correctly prunes irrelevant input and hidden units.