Information and Topology in Attractor Neural Networks

Authors:
D. Dominguez;K. Koroutchev;E. Serrano;F. B. Rodríguez
Affiliations:
david.dominguez@uam.es;k.koroutchev@uam.es;eduardo.serrano@uam.es;EPS, Universidad Autónoma de Madrid, 28049 Madrid, Spain, F.Rodriguez@uam.es
Venue:
Neural Computation
Year:
2007

Citing 3
Cited 2

Notions of associative memory and sparse coding

Neural Networks - 1996 Special issue: four major hypotheses in neuroscience
Mutual information of sparsely coded associative memory with self-control and ternary neurons

Neural Networks
Global and local synchrony of coupled neurons in small-world networks

Biological Cybernetics

Block attractor in spatially organized neural networks

Neurocomputing
Learning sequences of sparse correlated patterns using small-world attractor neural networks: An application to traffic videos

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A wide range of networks, including those with small-world topology, can be modeled by the connectivity ratio and randomness of the links. Both learning and attractor abilities of a neural network can be measured by the mutual information (MI) as a function of the load and the overlap between patterns and retrieval states. In this letter, we use MI to search for the optimal topology with regard to the storage and attractor properties of the network in an Amari-Hopfield model. We find that while an optimal storage implies an extremely diluted topology, a large basin of attraction leads to moderate levels of connectivity. This optimal topology is related to the clustering and path length of the network. We also build a diagram for the dynamical phases with random or local initial overlap and show that very diluted networks lose their attractor ability.