Synthesis of feedforward networks in supremum error bound

K Ciesielski; J P Sacha; K J Cios

doi:10.1109/72.883398

Synthesis of feedforward networks in supremum error bound

IEEE Trans Neural Netw. 2000;11(6):1213-27. doi: 10.1109/72.883398.

Authors

K Ciesielski¹, J P Sacha, K J Cios

Affiliation

¹ Department of Mathematics, West Virginia University, Morgantown, WV 26506, USA. K_cies@math.wvu.edu

PMID: 18249848
DOI: 10.1109/72.883398

Abstract

The main result of this paper is a constructive proof of a formula for the upper bound of the approximation error in Linfinity (supremum norm) of multidimensional functions by feedforward networks with one hidden layer of sigmoidal units and a linear output. This result is applied to formulate a new method of neural-network synthesis. The result can also be used to estimate complexity of the maximum-error network and/or to initialize that network weights. An example of the network synthesis is given.