Skip navigation
Skip navigation

Decision region approximation by polynomials or neural networks

Blackmore, Kim; Williamson, Robert C.; Mareels, Iven M. Y.


We give degree of approximation results for decision regions which are defined by polynomial and neural network parametrizations. The volume of the misclassified region is used to measure the approximation error, and results for the degree of L1 approximation of functions are used. For polynomial parametrizations, we show that the degree of approximation is at least 1, whereas for neural network parametrizations we prove the slightly weaker result that the degree of approximation is at least...[Show more]

CollectionsANU Research Publications
Date published: 1997-05
Type: Journal article
Source: IEEE Transactions on Information Theory 43.3 (1997): 903-907
DOI: 10.1109/18.568700


File Description SizeFormat Image
Blackmore_DecisionRegion1997.pdf291.47 kBAdobe PDFThumbnail

Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  20 July 2017/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator