{ "id": "cond-mat/9907390", "version": "v1", "published": "1999-07-26T13:05:44.000Z", "updated": "1999-07-26T13:05:44.000Z", "title": "Q-Ising neural network dynamics: a comparative review of various architectures", "authors": [ "D. Bolle", "G. Jongen", "G. M. Shim" ], "comment": "To appear in the proceedings of the Int. Conf. on Math. Phys. and Stochastic Analysis (Lisbon, October, 1998), ed. S. Albevero et all (World Scientific)", "categories": [ "cond-mat.dis-nn" ], "abstract": "This 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.", "revisions": [ { "version": "v1", "updated": "1999-07-26T13:05:44.000Z" } ], "analyses": { "keywords": [ "q-ising neural network dynamics", "comparative review", "architecture", "thermodynamic replica-symmetric mean-field theory approach", "symmetric networks equilibrium fixed-point equations" ], "note": { "typesetting": "TeX", "pages": 0, "language": "en", "license": "arXiv", "status": "editable", "adsabs": "1999cond.mat..7390B" } } }