Abstract
In this chapter we develop the memory model, a dynamical system neural network model which simulates memory retrieval. The time evolution of a trajectory of such a system is mathematical recognition, meaning convergence to one of several attractors referred to as mathematical memories. The attractors are prespecified constant trajectories or limit cycles. Thus mathematical recognition amounts to convergence from an input vector in n-dimensional space to one of the memories represented as an n-vector with components ±1.
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.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1991 Birkhäuser Boston
About this chapter
Cite this chapter
Jeffries, C. (1991). The Memory Model. In: Jeffries, C. (eds) Code Recognition and Set Selection with Neural Networks. Mathematical Modeling, vol 7. Birkhäuser Boston. https://doi.org/10.1007/978-1-4612-3216-2_4
Download citation
DOI: https://doi.org/10.1007/978-1-4612-3216-2_4
Publisher Name: Birkhäuser Boston
Print ISBN: 978-1-4612-7836-8
Online ISBN: 978-1-4612-3216-2
eBook Packages: Springer Book Archive