Sciweavers

IJCNN
2007
IEEE

Upper Bound on Pattern Storage in Feedforward Networks

14 years 6 months ago
Upper Bound on Pattern Storage in Feedforward Networks
—Starting from the strict interpolation equations for multivariate polynomials, an upper bound is developed for the number of patterns that can be memorized by a nonlinear feedforward network. A straightforward proof by contradiction is presented for the upper bound. It is shown that the hidden activations do not have to be analytic. Networks, trained by conjugate gradient, are used to demonstrate the tightness of the bound for random patterns. Based upon the upper bound, small multilayer perceptron models are successfully demonstrated for large support vector machines.
Pramod Lakshmi Narasimha, Michael T. Manry, Franci
Added 03 Jun 2010
Updated 03 Jun 2010
Type Conference
Year 2007
Where IJCNN
Authors Pramod Lakshmi Narasimha, Michael T. Manry, Francisco Maldonado
Comments (0)