Associative networks with diluted patterns: dynamical analysis at low and medium load

DOI10.1088/1751-8113/47/41/415001MaRDI QIDQ2927691zbMATH OpenOpenAlexWikidataFDO

Authors S. Bartolucci, A. Annibale

Publication date 4 November 2014

Published in Journal of Physics A: Mathematical and Theoretical (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1405.2454

zbMATH Keywords

disordered systemsneural networkssequential dynamics

Mathematics Subject Classification ID

Disordered systems (random Ising models, random Schrödinger operators, etc.) in equilibrium statistical mechanics (82B44)

Abstract: In this work we solve the dynamics of pattern diluted associative networks, evolving via sequential Glauber update. We derive dynamical equations for the order parameters, that quantify the simultaneous pattern recall of the system, and analyse the nature and stability of the stationary solutions by means of linear stability analysis as well as Monte Carlo simulations. We investigate the parallel retrieval capabilities of the system in different regions of the phase space, in particular in the low and medium storage regimes and for finite and extreme pattern dilution. Results show that in the absence of patterns cross-talk, all patterns are recalled symmetrically for any temperature below criticality, while in the presence of pattern cross-talk, symmetric retrieval becomes unstable as temperature is lowered and a hierarchical retrieval takes over. The shape of the hierarchical retrieval occurring at zero temperature is provided. The parallel retrieval capabilities of the network are seen to degrade gracefully in the regime of strong interference, but they are not destroyed.

Review text

Associative networks with diluted patterns have been introduced in [\textit{E. Agliari} et al., ``Multitasking associative networks, Phys. Rev. Lett. 109, Article ID 268101, 5 p. (2012; \url{doi:10.1103/PhysRevLett.109.268101})] as a generalization of the standard Hopfield model. In this paper, a dynamical analysis of associative memories with diluted patterns, evolving via Glauber sequential update is presented. Dynamical equations for a suitable set of macroscopic parameters, which quantify the (parallel) retrieval of the system are derived. The nature and stability of the steady-state solutions of the equations in different regions of the tunable parameters (noise, dilution, storage load) are investigated.

Recommendations

• Dynamical properties of a randomly diluted neural network with variable activity
• Multitasking attractor networks with neuronal threshold noise
• Dynamics of a neural network with hierarchically stored patterns
• Retrieval properties of diluted attractor neural networks
• scientific article; zbMATH DE number 1164156

Cited in

(10)

• Associative recall in non-randomly diluted neuronal networks
• Immune networks: multi-tasking capabilities at medium load
• A dynamical model of the adaptive immune system: effects of cells promiscuity, antigens and B-B interactions
• The role of idiotypic interactions in the adaptive immune system: a belief-propagation approach
• Dynamics of a neural network with hierarchically stored patterns
• Dynamical properties of a randomly diluted neural network with variable activity
• Multitasking attractor networks with neuronal threshold noise
• The role of the T-helper/T-suppressor ratio in the adaptive immune response: a dynamical model
• Slowly evolving connectivity in recurrent neural networks: I. The extreme dilution regime
• Interpolating between boolean and extremely high noisy patterns through minimal dense associative memories

This page was built for publication: Associative networks with diluted patterns: dynamical analysis at low and medium load

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2927691)