Thermodynamic properties of extremely diluted symmetricQ-Ising neural networks

DOI10.1088/0305-4470/33/37/302MaRDI QIDQ4520702zbMATH OpenOpenAlexFDO

Authors D. Bollé, Domenico M. Carlucci, G. M. Shim

Publication date 13 December 2000

Published in Journal of Physics A: Mathematical and General (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/cond-mat/0002200

zbMATH Keywords

de Almeida-Thouless lineextremely diluted symmetric \(Q\)-Ising neural networksreplica-symmetric mean-field theorythermodynamic and retrieval properties

Mathematics Subject Classification ID

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

Abstract: Using the replica-symmetric mean-field theory approach the thermodynamic and retrieval properties of extremely diluted {it symmetric} $Q$-Ising neural networks are studied. In particular, capacity-gain parameter and capacity-temperature phase diagrams are derived for $Q=3,4$ and $Q=infty$. The zero-temperature results are compared with those obtained from a study of the dynamics of the model. Furthermore, the de Almeida-Thouless line is determined. Where appropriate, the difference with other $Q$-Ising architectures is outlined.

Recommendations

• Thermodynamic properties of fully connected Q-Ising neural networks
• Parallel dynamics of extremely diluted symmetric \(Q\)-Ising neural networks
• \(Q\)-Ising neural network dynamics: A comparative review of various architectures
• The Ashkin-Teller neural network near saturation
• On the parallel dynamics of the \(Q\)-state Potts and \(Q\)-Ising neural networks

Cited in

(4)

• Parallel dynamics of extremely diluted symmetric \(Q\)-Ising neural networks
• Frozen 1-RSB structure of the symmetric Ising perceptron
• The Ashkin-Teller neural network near saturation
• \(Q\)-Ising neural network dynamics: A comparative review of various architectures

This page was built for publication: Thermodynamic properties of extremely diluted symmetricQ-Ising neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4520702)