Q-Ising neural network dynamics: a comparative review of various architectures

dc.creatorBolle, D.
dc.creatorJongen, G.
dc.creatorShim, G. M.
dc.date1999-07-26
dc.date.accessioned2026-07-25T23:50:00Z
dc.descriptionThis contribution reviews the parallel dynamics of Q-Ising neural networks for various architectures: extremely diluted asymmetric, layered feedforward, extremely diluted symmetric, and fully connected. Using a probabilistic signal-to-noise ratio analysis, taking into account all feedback correlations, which are strongly dependent upon these architectures the evolution of the distribution of the local field is found. This leads to a recursive scheme determining the complete time evolution of the order parameters of the network. Arbitrary Q and mainly zero temperature are considered. For the asymmetrically diluted and the layered feedforward network a closed-form solution is obtained while for the symmetrically diluted and fully connected architecture the feedback correlations prevent such a closed-form solution. For these symmetric networks equilibrium fixed-point equations can be derived under certain conditions on the noise in the system. They are the same as those obtained in a thermodynamic replica-symmetric mean-field theory approach.
dc.descriptionTo appear in the proceedings of the Int. Conf. on Math. Phys. and Stochastic Analysis (Lisbon, October, 1998), ed. S. Albevero et all (World Scientific)
dc.identifierhttps://arxiv.org/abs/cond-mat/9907390
dc.identifierhttp://arxiv.org/abs/cond-mat/9907390
dc.identifier.urihttps://dspace.dare.co.zw/handle/123456789/101829
dc.subjectDisordered Systems and Neural Networks
dc.titleQ-Ising neural network dynamics: a comparative review of various architectures
dc.typetext

Files