Abstract
An architecture based on networks of logic functions is proposed with the output of the network forming a model or archetype image of the class of pattern stimulating the net. Frequency of occurrence information which relates the output of each function to the number of times the stimulus sampled in the test pattern has occurred during the training phase is used. This is shown to have significant advantages over simple binary systems and networks with progressively decreasing connectivity during training-the so called 'ageing 'effect. The frequency of occurrence networks are no longer sensitive to the sequence or order of the training categories and have a greatly improved noise stability. The network is assessed with real world data made up of some hundreds of examples of machine printed numerals.
Preview
Unable to display preview. Download preview PDF.
References
Fairhurst, M.C., ‘Natural pattern clustering in digital learning nets'. Electronic letters, 1971, Vol. 7, P724.
Stonham, T.J., Wilkie, B.A. and Masih, L., ‘Higher order Adaptive Networks-Some aspects of multi-class and feedback systems'. Proceeding of the Third Alvey Vision Conference, Cambridge, 1987, P245.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1988 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Masih, L., Stonham, T.J. (1988). Convergence in a learning network with pattern feedback. In: Kittler, J. (eds) Pattern Recognition. PAR 1988. Lecture Notes in Computer Science, vol 301. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-19036-8_9
Download citation
DOI: https://doi.org/10.1007/3-540-19036-8_9
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-19036-3
Online ISBN: 978-3-540-38947-7
eBook Packages: Springer Book Archive