2005/06/21 by D. Dominguez, David Domínguez, K. Koroutchev +9
Computer Science · Engineering · Physics and Astronomy · #Advanced Memory and Neural Computing #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Physical sciences #Neural Networks and Applications #Neural Networks and Reservoir Computing #Statistical Mechanics (cond-mat.stat-mech) #cond-mat.dis-nn #cond-mat.stat-mech
paper · pdf · doi:10.48550/arxiv.cond-mat/0506535
7 pgs., 5 figs
arxiv created 2005/06/21 · openalex publication_date 2005/06/21 · arxiv updated 2009/12/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
A wide range of networks, including small-world topology, can be modelled by the connectivity γ, and randomness ω 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 rate and overlap between patterns and retrieval states. We use MI to search for the optimal topology, for storage and attractor properties of the network. We find that, while the largest storage implies an optimal MI(γ,ω) at γopt(ω)→ 0, the largest basin of attraction leads to an optimal topology at moderate levels of γopt, whenever 0≤ω<0.3. This γopt is related to the clustering and path-length of the network. We also build a diagram for the dynamical phases with random and local initial overlap, and show that very diluted networks lose their attractor ability.