A new mechanical approach to handle generalized Hopfield neural networks

DOI10.1016/j.neunet.2018.07.010zbMath1451.82043OpenAlexW2883260865WikidataQ90777882 ScholiaQ90777882MaRDI QIDQ2182875

Alberto Fachechi, Adriano Barra, Matteo Beccaria

Publication date: 26 May 2020

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2018.07.010

zbMATH Keywords

statistical mechanicsHopfield networksnon-linear PDErelativistic mechanicsunlearning

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Learning and adaptive systems in artificial intelligence (68T05) Neural nets applied to problems in time-dependent statistical mechanics (82C32) Monte Carlo methods applied to problems in statistical mechanics (82M31)

Related Items (11)

Solving the TSP by the AALHNN algorithm ⋮ On the Marchenko–Pastur law in analog bipartite spin-glasses ⋮ Interpolating between boolean and extremely high noisy patterns through minimal dense associative memories ⋮ Replica symmetry breaking in dense Hebbian neural networks ⋮ The relativistic Hopfield network: Rigorous results ⋮ Dreaming neural networks: rigorous results ⋮ 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 ⋮ Intermittent boundary stabilization of stochastic reaction-diffusion Cohen-Grossberg neural networks ⋮ Replica symmetry breaking in neural networks: a few steps toward rigorous results

Uses Software

• CUDA

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Optimization by Simulated Annealing
• Multitasking attractor networks with neuronal threshold noise
• Parallel retrieval of correlated patterns: from Hopfield networks to Boltzmann machines
• The mean field Ising model trough interpolating techniques
• ``Neural computation of decisions in optimization problems
• Gibbs states of the Hopfield model in the regime of perfect memory
• The retrieval phase of the Hopfield model: A rigorous analysis of the overlap distribution
• 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
• 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
• Thermodynamics of restricted Boltzmann machines and related learning dynamics
• Equilibrium statistical mechanics of bipartite spin systems
• Replica symmetry breaking in mean-field spin glasses through the Hamilton–Jacobi technique
• Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
• A mechanical approach to mean field spin models
• Statistical mechanics of Hopfield-like neural networks with modified interactions
• Modeling Brain Function
• Unlearning in the paramagnetic phase of neural network models
• Integrable viscous conservation laws
• Neural networks and physical systems with emergent collective computational abilities.
• On quantum and relativistic mechanical analogues in mean-field spin models
• On integrable conservation laws
• The space of interactions in neural network models

This page was built for publication: A new mechanical approach to handle generalized Hopfield neural networks