Summary: Adaptive averaging in higher order neural networks for
invariant pattern recognition
Sabine Kr¨oner
Technische Informatik I
TU Hamburg­Harburg
D--21071 Hamburg
Phone: +49 [40] 7718 2539
Fax: +49 [40] 7718 2911
E­mail: kroener@tu­harburg.d400.de
ABSTRACT
For the task of position­, scale­, and rotation­invariant pattern recognition higher order
neural networks have shown good separation results for different object classes. However,
their use is limited by the large number of monomials that have to be calculated to get the
invariant features. Even with the application of methods like coarse coding to reduce the
number of monomials the computational requirements are still large.
Here a new method is proposed where the averaging of the monomials to form the invariant
features is performed adaptively with a network architecture that uses coupled nodes. Thereby
the features are adapted to a specific application. This reduces significantly the number and
order of the monomials necessary for the invariant recognition of patterns. Moreover, the
classification part of the network becomes superfluous since the output of the network is

Source: Albert-Ludwigs-Universität Freiburg, Institut für Informatik,, Lehrstuhls für Mustererkennung und Bildverarbeitung

Collections: Computer Technologies and Information Sciences