Abstract
In a biological context one is used to examples in which the properties of organisms are adapted to provide efficient operation in their particular environments, with otherwise similar systems differing in appropriate details when their environments are different. In this talk we demonstrate a similar phenomenon in some simple neural networks. In particular, we consider the performance of dilute attractor neural networks for associative memory with respect to optimal performances as characterized by two different measures, retrieval overlap and size of the basin from which retrieval is possible. We believe however that our conclusions are more broadly applicable1.
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
K. Y. M. Wong and D. Sherrington, Optimally adapted attractor neural network in the presence of noise, J. Phys. A in press (1990).
B. Derrida, E. Gardner and A. Zippelius, An exactly solvable asymmetric neural network model, Europhys. Lett. 4: 167 (1987).
D. Amit, M. Evans, H. Horner and K. Y. M. Wong, Retrieval phase diagrams for attractor neural networks with optimal interactions, J. Phys. A 23: 3361 (1990).
K. Y. M. Wong and D. Sherrington, Training noise adaptation in attractor neural networks, J. Phys. A 23: L175 (1990).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1991 Springer Science+Business Media New York
About this chapter
Cite this chapter
Sherrington, D., Wong, K.Y.M. (1991). Specialization, Adaptation and Optimization in Dilute Random Attractor Neural Networks. In: Peliti, L. (eds) Biologically Inspired Physics. NATO ASI Series, vol 263. Springer, Boston, MA. https://doi.org/10.1007/978-1-4757-9483-0_24
Download citation
DOI: https://doi.org/10.1007/978-1-4757-9483-0_24
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4757-9485-4
Online ISBN: 978-1-4757-9483-0
eBook Packages: Springer Book Archive