The main result of this paper is a constructive proof of a formula for the upper bound of the approximation error in L\infty (supremum norm) of multi-dimensional 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.
Full text on line in pdf format. Requires Adobe Acrobat Reader.
Full text in postscript form.
Text in dvi format. (No pictures included.)
Last modified January 20, 2014.