Dreaming neural networks: rigorous results

DOI10.1088/1742-5468/ab371dzbMath1457.82322arXiv1812.09077OpenAlexW3098745735MaRDI QIDQ5134375

Alberto Fachechi, Francesco Alemanno, Elena Agliari, Adriano Barra

Publication date: 16 November 2020

Published in: Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1812.09077

Mathematics Subject Classification ID

Random graphs (graph-theoretic aspects) (05C80) Statistical mechanics of random media, disordered materials (including liquid crystals and spin glasses) (82D30) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Related Items (10)

Interpolating between boolean and extremely high noisy patterns through minimal dense associative memories ⋮ Replica symmetry breaking in dense Hebbian neural networks ⋮ Interacting dreaming neural networks ⋮ On the effective initialisation for restricted Boltzmann machines via duality with Hopfield model ⋮ The decimation scheme for symmetric matrix factorization ⋮ Generalized Guerra's interpolation schemes for dense associative neural networks ⋮ PDE/statistical mechanics duality: relation between Guerra's interpolated \(p\)-spin ferromagnets and the Burgers hierarchy ⋮ The relativistic Hopfield model with correlated patterns ⋮ Learning and retrieval operational modes for three-layer restricted Boltzmann machines ⋮ Replica symmetry breaking in neural networks: a few steps toward rigorous results

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multitasking attractor networks with neuronal threshold noise
• Parallel retrieval of correlated patterns: from Hopfield networks to Boltzmann machines
• Gibbs states of the Hopfield model in the regime of perfect memory
• Rigorous results for the Hopfield model with many patterns
• Gibbs states of the Hopfield model with extensively many patterns.
• Neural networks retrieving Boolean patterns in a sea of Gaussian ones
• On the stability of the quenched state in mean-field spin-glass models
• Exponential inequalities and convergence of moments in the replica-symmetric regime of the Hopfield model.
• The replica-symmetric solution without replica trick for the Hopfield model
• On the equivalence of Hopfield networks and Boltzmann machines
• A new mechanical approach to handle generalized Hopfield neural networks
• Spin-glass stochastic stability: a rigorous proof
• Statistical Mechanics of Learning
• Entropy landscape of solutions in the binary perceptron problem
• Immune networks: multitasking capabilities near saturation
• Universality in bipartite mean field spin glasses
• Equilibrium statistical mechanics of bipartite spin systems
• About the ergodic regime in the analogical Hopfield neural networks: Moments of the partition function
• Statistical mechanics of Hopfield-like neural networks with modified interactions
• Replica symmetry breaking in neural networks with modified pseudo-inverse interactions
• Modeling Brain Function
• On the replica symmetric equations for the Hopfield model
• Unlearning in the paramagnetic phase of neural network models
• Free energies of Boltzmann machines: self-averaging, annealed and replica symmetric approximations in the thermodynamic limit
• Neural networks and physical systems with emergent collective computational abilities.
• Determining computational complexity from characteristic ‘phase transitions’
• Gibbs states and the set of solutions of random constraint satisfaction problems
• The space of interactions in neural network models
• The replica symmetric approximation of the analogical neural network

This page was built for publication: Dreaming neural networks: rigorous results