The capacity of \(q\)-state Potts neural networks with parallel retrieval dynamics

DOI10.1016/j.spl.2007.03.030zbMath1137.82018MaRDI QIDQ2467386

Franck Vermet, Matthias Loewe

Publication date: 21 January 2008

Published in: Statistics \& Probability Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.spl.2007.03.030

zbMATH Keywords

storage capacity; Hopfield model; Potts neural network

Mathematics Subject Classification ID

60K35: Interacting random processes; statistical mechanics type models; percolation theory

82B44: Disordered systems (random Ising models, random Schrödinger operators, etc.) in equilibrium statistical mechanics

82C32: Neural nets applied to problems in time-dependent statistical mechanics

Related Items

Capacity bounds for the CDMA system and a neural network: a moderate deviations approach, A comparative study of sparse associative memories, The Hopfield model on a sparse Erdös-Renyi graph, Index structures for fast similarity search for binary vectors, Opinion formation in a heterogeneous population --- a new approach to the Hopfield model, The swapping algorithm for the Hopfield model with two patterns, On a model of associative memory with huge storage capacity, Capacity of an associative memory model on random graph architectures

Cites Work

• Lower bounds on the restitution error in the Hopfield model
• A lower bound for the memory capacity in the Potts-Hopfield model
• Thermodynamic limit of the \(q\)-state Potts-Hopfield model with infinitely many patterns
• Negative association of random variables, with applications
• The capacity of the Hopfield associative memory
• Nondirect convergence radius and number of iterations of the Hopfield associative memory
• Sharp upper bounds on perfect retrieval in the Hopfield model
• Neural networks and physical systems with emergent collective computational abilities.
• Unnamed Item
• Unnamed Item