Structured Information in Metric Neural Networks

2005/07/29 by David Domínguez, Dominguez, David, Kostadin Koroutchev +4
Computer Science · Neuroscience · #Adaptation and Self-Organizing Systems (nlin.AO) #Evolutionary Algorithms and Applications #Exactly Solvable and Integrable Systems (nlin.SI) #FOS: Physical sciences #Neural Networks and Applications #Neural dynamics and brain function

paper · pdf · doi:10.48550/arxiv.nlin/0507066

openalex publication_date 2005/07/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The retrieval abilities of spatially uniform attractor networks can be measured by the average overlap between patterns and neural states. We found that metric networks, with local connections, however, can carry information structured in blocks without any global overlap. and blocks attractors. We propose a way to measure the block information, related to the fluctuation of the overlap. The phase-diagram with the transition from local to global information, shows that the stability of blocks grows with dilution, but decreases with the storage rate and disappears for random topologies.

Related

• Information and Topology in Attractor Neural Network
• Influence of topology on the performance of a neural network
• Dynamical Neural Network: Information and Topology
• Information content in continuous attractor neural networks is preserved in the presence of moderate disordered background connectivity
• Information Capacity of a Hierarchical Neural Network