Analogue neural networks on correlated random graphs

Abstract

We consider a generalization of the Hopfield model, where the entries of patterns are Gaussian and diluted. We focus on the high-storage regime and we investigate analytically the topological properties of the emergent network, as well as the thermodynamic properties of the model. We find that, by properly tuning the dilution in the pattern entries, the network can recover different topological regimes characterized by peculiar scalings of the average coordination number with respect to the system size. The structure is also shown to exhibit a large degree of cliquishness, even when very sparse. Moreover, we obtain explicitly the replica symmetric free energy and the self-consistency equations for the overlaps (order parameters of the theory), which turn out to be classical weighted sums of 'sub-overlaps' defined on all possible sub-graphs. Finally, a study of criticality is performed through a small-overlap expansion of the self-consistencies and through a whole fluctuation theory developed for their rescaled correlations: Both approaches show that the net effect of dilution in pattern entries is to rescale the critical noise level at which ergodicity breaks down.

arXiv comment34 pages, 3 figures

References in corpus (21)

• Critical phenomena in complex networks
• The Thermodynamic Limit in Mean Field Spin Glass Models
• General properties of overlap probability distributions in disordered spin systems. Toward Parisi ultrametricity
• On the Stability of the Quenched State in Mean Field Spin Glass Models
• Multitasking associative networks
• Statistical Mechanics of Support Vector Networks
• The replica symmetric behavior of the analogical neural network
• The high temperature region of the Viana-Bray diluted spin glass model
• Finite Connectivity Attractor Neural Networks
• A thermodynamical perspective of immune capabilities
• Analytic solution of attractor neural networks on scale-free graphs
• A Hebbian approach to complex network generation
• Criticality in diluted ferromagnet
• Stochastic symmetry-breaking in a gaussian Hopfield model
• Percolation on correlated random networks
• A spherical Hopfield model
• Interpolating the Sherrington-Kirkpatrick replica trick
• Organization and evolution of synthetic idiotypic networks
• Equilibrium statistical mechanics on correlated random graphs
• Stochastic Stability: a Review and Some Perspectives
• Infinitely many states and stochastic symmetry in a Gaussian Potts-Hopfield model

Cited by in corpus (6)

• Meta-stable states in the hierarchical Dyson model drive parallel processing in the hierarchical Hopfield network
• Another look at the Gardner problem
• A walk in the statistical mechanical formulation of neural networks
• Discrete perceptrons
• Spherical perceptron as a storage memory with limited errors
• Negative spherical perceptron