Analytic solution of attractor neural networks on scale-free graphs

Abstract

We study the influence of network topology on retrieval properties of recurrent neural networks, using replica techniques for diluted systems. The theory is presented for a network with an arbitrary degree distribution $p(k)$ and applied to power law distributions $p(k)\sim k^{-\gamma }$, i.e. to neural networks on scale-free graphs. A bifurcation analysis identifies phase boundaries between the paramagnetic phase and either a retrieval phase or a spin glass phase. Using a population dynamics algorithm, the retrieval overlap and spin glass order parameters may be calculated throughout the phase diagram. It is shown that there is an enhancement of the retrieval properties compared with a Poissonian random graph. We compare our findings with simulations.

11 pages, 5 eps figures, LaTeX

References in corpus (1)

• Slowly evolving random graphs II: Adaptive geometry in finite-connectivity Hopfield models

Cited by in corpus (20)

• Entropies of complex networks with hierarchically constrained topologies
• Immune networks: multi-tasking capabilities near saturation
• The Cavity Approach to Parallel Dynamics of Ising Spins on a Graph
• Finitely connected vector spin systems with random matrix interactions
• Cavity approach for real variables on diluted graphs and application to synchronization in small-world lattices
• Parallel dynamics of disordered Ising spin systems on finitely connected directed random graphs with arbitrary degree distributions
• Dynamical replica analysis of disordered Ising spin systems on finitely connected random graphs
• Hierarchical neural networks perform both serial and parallel processing
• Parallel processing in immune networks
• Toward a quantitative approach to migrants integration
• Replica symmetry breaking in the `small world' spin glass
• Dynamical replica analysis of processes on finitely connected random graphs II: Dynamics in the Griffiths phase of the diluted Ising ferromagnet
• Spin models on random graphs with controlled topologies beyond degree constraints
• Meta-stable states in the hierarchical Dyson model drive parallel processing in the hierarchical Hopfield network
• Phase transitions in the three-state Ising spin-glass model with finite connectivity
• Enhanced storage capacity with errors in scale-free Hopfield neural networks: an analytical study
• Equilibrium statistical mechanics on correlated random graphs
• Analogue neural networks on correlated random graphs
• On metastable configurations of small-world networks
• Mean-field theory of vector spin models on networks with arbitrary degree distributions