Rigorous bounds on the storage capacity of the dilute Hopfield model

DOI10.1007/BF01050427zbMath0900.82064MaRDI QIDQ1379377

Véronique Gayrard, Anton Bovier

Publication date: 22 March 1998

Published in: Journal of Statistical Physics (Search for Journal in Brave)

zbMATH Keywords

memory capacitybond dilutiondendritic connection

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Related Items (12)

Iterated large deviations ⋮ Exact recovery in block spin Ising models at the critical line ⋮ On some spectral properties of large self-dual dilute quaternion random matrices ⋮ Eigenvalue distribution of large dilute random matrices ⋮ Graph Degree Sequence Solely Determines the Expected Hopfield Network Pattern Stability ⋮ The Hopfield model on a sparse Erdös-Renyi graph ⋮ Rigorous results on the thermodynamics of the dilute Hopfield model ⋮ Capacity of an associative memory model on random graph architectures ⋮ Large deviation principles for the Hopfield model and the Kac-Hopfield model ⋮ On the free energy of the Hopfield model ⋮ Unnamed Item ⋮ On the storage capacity of Hopfield models with correlated patterns

Cites Work

• Some rigorous results on the Hopfield neural network model
• Long term memory storage capacity of multiconnected neural networks
• A lower bound for the memory capacity in the Potts-Hopfield model
• Analytic study of the memory storage capacity of a neural network
• Thermodynamic limit of the \(q\)-state Potts-Hopfield model with infinitely many patterns
• The capacity of the Hopfield associative memory
• Metastable states in asymmetrically diluted Hopfield networks
• Neural potentials as stimuli for attractor neural networks
• Neural networks and physical systems with emergent collective computational abilities.

This page was built for publication: Rigorous bounds on the storage capacity of the dilute Hopfield model