Parallel dynamics of extremely diluted symmetric Q-Ising neural networks

DOI10.1023/A:1004662710179MaRDI QIDQ1964512zbMATH OpenOpenAlexFDO

Authors D. Bollé, G. Jongen, G. M. Shim

Publication date 20 February 2000

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

Full work available at URL https://arxiv.org/abs/cond-mat/9810386

zbMATH Keywords

parallel dynamics\(Q\)-Ising neural networksextremely diluted symmetric networks

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Abstract: The parallel dynamics of extremely diluted symmetric Q-Ising neural networks is studied for arbitrary Q using a probabilistic approach. In spite of the extremely diluted architecture the feedback correlations arising from the symmetry prevent a closed-form solution in contrast with the extremely diluted asymmetric model. A recursive scheme is found determining the complete time evolution of the order parameters taking into account all feedback. It is based upon the evolution of the distribution of the local field, as in the fully connected model. As an illustrative example an explicit analysis is carried out for the Q=2 and Q=3 model. These results agree with and extend the partial results existing for Q=2. For Q>2 the analysis is entirely new. Finally, equilibrium fixed-point equations are derived and a capacity-gain function diagram is obtained.

Recommendations

• Parallel dynamics of fully connected \(Q\)-Ising neural networks
• \(Q\)-Ising neural network dynamics: A comparative review of various architectures
• On the parallel dynamics of the \(Q\)-state Potts and \(Q\)-Ising neural networks
• Thermodynamic properties of extremely diluted symmetricQ-Ising neural networks
• scientific article; zbMATH DE number 1329969

Cited in

(10)

• Frozen 1-RSB structure of the symmetric Ising perceptron
• Thermodynamic properties of extremely diluted symmetricQ-Ising neural networks
• Asymmetrically extremely dilute neural networks with Langevin dynamics and unconventional results
• Parallel dynamics of the fully connected Blume-Emery-Griffiths neural network
• \(Q\)-Ising neural network dynamics: A comparative review of various architectures
• Neural networks enforcing physical symmetries in nonlinear dynamical lattices: the case example of the Ablowitz-Ladik model
• scientific article; zbMATH DE number 125399 (Why is no real title available?)
• Thermodynamic properties of fully connected Q-Ising neural networks
• Parallel dynamics of fully connected \(Q\)-Ising neural networks
• Information and Topology in Attractor Neural Networks

This page was built for publication: Parallel dynamics of extremely diluted symmetric \(Q\)-Ising neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1964512)