Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

5

IWANN
1999
Springer

favoriteEmaildiscussreport

101views Neural Networks» more IWANN 1999»

The Capacity and Attractor Basins of Associative Memory Models

13 years 9 months ago

The Capacity and Attractor Basins of Associative Memory Models

Download homepages.feis.herts.ac.uk

The performance characteristics of five variants of the Hopfield network are examined. Two performance metrics are used: memory capacity, and a measure of the size of basins of attraction. We find that the posttraining adjustment of processor thresholds has, at best, little or no effect on performance, and at worst a significant negative effect. The adoption of a local learning rule can, however, give rise to significant performance gains.

Neil Davey, S. P. Hunt

Real-time Traffic

IWANN 1999 | Neural Networks | Performance Metrics | Significant Negative Effect | Significant Performance Gains |

claim paper

Related Content

» Topologically Continuous Associative Memory A Theoretical Foundation

» Image retrieval and classification using associative reciprocalimage attractors

» Studies on the Memory Capacity and Robustness of Chaotic Dynamic Neural Networks

» Attractor Network Models of Cortical Associative Memory

» Attractor dynamics in a modular network model of the cerebral cortex

» High capacity small world associative memory models

» Efficient architectures for sparselyconnected high capacity associative memory models

» Evolution of discrete gene regulatory models

» Learning Shapes Bifurcations of Neural Dynamics upon External Stimuli

Post Info
More Details (n/a)

Added	04 Aug 2010
Updated	04 Aug 2010
Type	Conference
Year	1999
Where	IWANN
Authors	Neil Davey, S. P. Hunt

Comments (0)