Technical Reports

1992

@techreport{HoA1993,
	vgclass =	{report},
	vgproject =	{nn},
	author =	{Sean B. Holden and Martin Anthony},
	title =	{Quantifying Generalization in Linearly Weighted Neural
	Networks},
	number =	{LSE-MPS-42},
	institution =	{London School of Economics Mathematics},
	month =	{December},
	year =	{1992},
	abstract =	{The Vapnik-Chervonenkis dimension has proven to be of
	great use in the theoretical study of generalization in artificial
	neural networks.  The `probably approximately correct' learning
	framework is described and the importance of the VC dimension is
	illustrated. We then investigate the VC dimension of certain types of
	linearly weighted neural networks. First, we obtain bounds on the VC
	dimensions of radial basis function networks with basis functions of
	several types. Secondly, we calculate the VC dimension of polynomial
	discriminant functions defined over both real and binary-valued
	inputs.},
}