Abstract
When using self-adjusting networksystems for modelling cognitive processes one has to remember that network systems have several limitations according to their respective design. For example, there are limits to the capacity which, if exceeded, make the system suddenly ‘forget’ everything in the sense of a ‘total confusion’ because of the superposition of the memory traces. Recently, attempts have been made to solve this problem, for example by implementing the ability to gradually ‘forget’ former memory traces.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Rumelhart, D.E., Hinton, G.E., Williams, R.J. (1986). Learning Internal Representation by Error Propagation. In D.E. Rumelhart, & J.L. McClelland (1986). Parallel Distributed Processing. Explorations in the Microstructure of Cognition. (vol. 1) Foundations. Part II: Basic Mechanisms, Chapter 8, MIT Press. Cambridge.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1989 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Müller, M. (1989). Rules for parallelprocessing networks with adaptive structure. In: Roskam, E.E. (eds) Mathematical Psychology in Progress. Recent Research in Psychology. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-83943-6_14
Download citation
DOI: https://doi.org/10.1007/978-3-642-83943-6_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-51686-6
Online ISBN: 978-3-642-83943-6
eBook Packages: Springer Book Archive