Topology and Dynamics of Attractor Neural Networks: The Role of Loopiness

Simple item page
dc.creatorZhang, Pan
dc.creatorChen, Yong
dc.date2007-03-15
dc.date2008-05-11
dc.date.accessioned2026-07-07T09:37:52Z
dc.date.available2026-07-07T09:37:52Z
dc.descriptionWe derive an exact representation of the topological effect on the dynamics of sequence processing neural networks within signal-to-noise analysis. A new network structure parameter, loopiness coefficient, is introduced to quantitatively study the loop effect on network dynamics. The large loopiness coefficient means the large probability of finding loops in the networks. We develop the recursive equations for the overlap parameters of neural networks in the term of the loopiness. It was found that the large loopiness increases the correlations among the network states at different times, and eventually it reduces the performance of neural networks. The theory is applied to several network topological structures, including fully-connected, densely-connected random, densely-connected regular, and densely-connected small-world, where encouraging results are obtained.
dc.description6 pages, 4 figures, comments are favored
dc.identifierhttps://arxiv.org/abs/cond-mat/0703405
dc.identifierhttp://arxiv.org/abs/cond-mat/0703405
dc.identifierPhysica A 387, (2008) 4411-4416
dc.identifierdoi:10.1016/j.physa.2008.02.073
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/160608
dc.subjectDisordered Systems and Neural Networks
dc.subjectStatistical Mechanics
dc.titleTopology and Dynamics of Attractor Neural Networks: The Role of Loopiness
dc.typetext

Files

Collections

arXiv