Related Experiment Video
Updated: Sep 26, 2026

Appetitive Associative Olfactory Learning in Drosophila Larvae
Published on: February 18, 2013
The basins of attraction of a new Hopfield learning rule
1Neural Systems Group, Department of Electrical and Electronic Engineering Imperial College, University of London, London, UK
Abstract:
The nature of the basins of attraction of a Hopfield network is as important as the capacity. Here a new learning rule is re-introduced. This learning rule has a higher capacity than that of the Hebb rule, and still keeps important functionality, such as incrementality and locality, which the pseudo-inverse lacks. However the basins of attraction of the fixed points of this learning rule have not yet been studied. Three important characteristics of basins of attraction are considered: indirect and direct basins of attraction, distribution of sizes of basins of attraction and the shape of the basins of attraction. The results for the new learning rule are compared with those of the Hebb rule. The size of direct and indirect basins of attractions are generally larger for the new rule than for the Hebb rule, the distribution of sizes is more even, and the shape of the basins more round.
Related Concept Videos
Woodward–Hoffmann Selection Rules and Microscopic Reversibility
Associative Learning
Classical conditioning, also known...
Root Loci for Positive-Feedback Systems
The construction rules for the root locus in positive feedback systems are similar to those in...
Observational Learning
Factors Influencing Attraction I: Proximity
Criteria for Aromaticity and the Hückel 4n + 2 Rule
For the first time, Eric Hückel, a German chemical physicist, derived a set of structural features for a compound to be classified as aromatic. This is now known as Hückel’s rule or the 4n + 2 rule.