The replica symmetric behavior of the analogical neural network

Abstract

In this paper we continue our investigation of the analogical neural network, paying interest to its replica symmetric behavior in the absence of external fields of any type. Bridging the neural network to a bipartite spin-glass, we introduce and apply a new interpolation scheme to its free energy that naturally extends the interpolation via cavity fields or stochastic perturbations to these models. As a result we obtain the free energy of the system as a sum rule, which, at least at the replica symmetric level, can be solved exactly. As a next step we study its related self-consistent equations for the order parameters and their rescaled fluctuations, found to diverge on the same critical line of the standard Amit-Gutfreund-Sompolinsky theory.

17 pages

References in corpus (4)

• Broken Replica Symmetry Bounds in the Mean Field Spin Glass Model
• The Thermodynamic Limit in Mean Field Spin Glass Models
• About the overlap distribution in mean field spin glass models
• The mean field Ising model trough interpolating techniques

Cited by in corpus (37)

• Multitasking associative networks
• Equilibrium statistical mechanics of bipartite spin systems
• Phase Diagram of Restricted Boltzmann Machines and Generalised Hopfield Networks with Arbitrary Priors
• Phase transitions in Restricted Boltzmann Machines with generic priors
• Immune networks: multi-tasking capabilities near saturation
• A thermodynamical perspective of immune capabilities
• Fundamental limits of low-rank matrix estimation: the non-symmetric case
• How glassy are neural networks?
• A Hebbian approach to complex network generation
• Neural networks with redundant representation: detecting the undetectable
• Universality in bipartite mean field spin glasses
• Non-Convex Multi-species Hopfield models
• Neural Networks retrieving Boolean patterns in a sea of Gaussian ones
• Dreaming neural networks: rigorous results
• Hierarchical neural networks perform both serial and parallel processing
• Mean field bipartite spin models treated with mechanical techniques
• Parallel processing in immune networks
• Dense Hebbian neural networks: a replica symmetric picture of supervised learning
• Replica symmetry breaking in multi-species Sherrington-Kirkpatrick model
• Interpolating the Sherrington-Kirkpatrick replica trick
• Meta-stable states in the hierarchical Dyson model drive parallel processing in the hierarchical Hopfield network
• Generalized hetero-associative neural networks
• Legendre Equivalences of Spherical Boltzmann Machines
• Equilibrium statistical mechanics on correlated random graphs
• Parallel Learning by Multitasking Neural Networks
• Free energies of Boltzmann Machines: self-averaging, annealed and replica symmetric approximations in the thermodynamic limit
• Analogue neural networks on correlated random graphs
• The Relativistic Hopfield network: rigorous results
• Interpolating between boolean and extremely high noisy patterns through Minimal Dense Associative Memories
• A Solvable Mean Field Model of a Gaussian Spin Glass
• Bounding ground state energy of Hopfield models
• Multi-species mean-field spin-glasses. Rigorous results
• On the equivalence of Hopfield Networks and Boltzmann Machines
• Asymmetric Little model and its ground state energies
• Localization and free energy asymptotics in disordered statistical mechanics and random growth models
• Supervised and Unsupervised protocols for hetero-associative neural networks
• Lifting/lowering Hopfield models ground state energies