Structured Information in Metric Neural Networks

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.