Stochastic symmetry-breaking in a gaussian Hopfield model

Abstract

We study a ``two-pattern'' Hopfield model with Gaussian disorder. We find that there are infinitely many pure states at low temperatures in this model, and we find that the metastate is supported on an infinity of symmetric pairs of pure states. The origin of this phenomenon is the random breaking of a rotation symmetry of the distribution of the disorder

31pp, AMSTeX

References in corpus (3)

• The metastate approach to thermodynamic chaos
• Simplicity of State and Overlap Structure in Finite-Volume Realistic Spin Glasses
• Metastates in the Hopfield model in the replica symmetric regime

Cited by in corpus (15)

• Phase Diagram of Restricted Boltzmann Machines and Generalised Hopfield Networks with Arbitrary Priors
• The replica symmetric behavior of the analogical neural network
• How glassy are neural networks?
• Neural Networks retrieving Boolean patterns in a sea of Gaussian ones
• Toward a quantitative approach to migrants integration
• On the Ising model with random boundary condition
• Metastates in finite-type mean-field models: visibility, invisibility, and random restoration of symmetry
• Incoherent boundary conditions and metastates
• Analogue neural networks on correlated random graphs
• Realistic spin glasses below eight dimensions: a highly disordered view
• High Temperature Asymptotics of Orthogonal Mean-Field Spin Glasses
• Infinitely many states and stochastic symmetry in a Gaussian Potts-Hopfield model
• A generalized Hopfield model to store and retrieve mismatched memory patterns
• Computational Bottlenecks of Quantum Annealing
• Metastates in mean-field models with random external fields generated by Markov chains