Pruning neural networks by minimization of the estimated variance
Peter Morgan, Bruce Curry, Malcom Beynon · European Journal of Economic and Social Systems · 2000
This paper presents a series of results on a method of pruning neural networks.An approximation to the estimated variance of errors, V, is constructed containing a supplementary parameter, α -the estimated variance itself being the limit of the function, V, as α tends to zero.The network weights are fitted using a minimization algorithm with V as objective function.The parameter, α, is reduced successively in the course of fitting.Results are presented using synthetic functions and the well-known airline passenger data.We find, for example, that the network can discover, in the course of being pruned, evidence of redundancy in the variables.