Refereed full papers (journals, book chapters, international conferences)

1992

@article{KrH1992,
	vgclass =	{refpap},
	vgproject =	{nn},
	author =	{Anders Krogh and John A. Hertz},
	title =	{A simple weight decay can improve generalisation},
	journal =	{Advances in Neural Information Processing Systems},
	volume =	{4},
	pages =	{950--957},
	year =	{1992},
	abstract =	{It has been observed in
	numerical simulations that a weight decay can improve generalization in
	a feed forward neural network.  This paper explains why. It is proven
	that a weight decay has two effects in a linear network. First, it
	suppresses any irrelevant components of the weight vector by choosing
	the smallest vector that solves the learning problem. Second, if the
	size is chosen right, a weight decay can suppress some of the effects
	of static noise on the targets, which improves generalization quite a
	lot. It is then shown how to extend these results to networks with
	hidden layers and non-linear units. Finally the theory is confirmed by
	some numerical simulations using the data from NetTalk.},
}