Higher-Order Neutral Networks, Polya Polynomials, and Fermi Cluster Diagrams

Simple item page
dc.creatorKurten, K. E.
dc.creatorClark, J. W.
dc.date2001-09-04
dc.date.accessioned2026-07-07T02:42:38Z
dc.date.available2026-07-07T02:42:38Z
dc.descriptionThe problem of controlling higher-order interactions in neural networks is addressed with techniques commonly applied in the cluster analysis of quantum many-particle systems. For multi-neuron synaptic weights chosen according to a straightforward extension of the standard Hebbian learning rule, we show that higher-order contributions to the stimulus felt by a given neuron can be readily evaluated via Polyà's combinatoric group-theoretical approach or equivalently by exploiting a precise formal analogy with fermion diagrammatics.
dc.description11 pages, 1 figure
dc.identifierhttps://arxiv.org/abs/cond-mat/0109053
dc.identifierhttp://arxiv.org/abs/cond-mat/0109053
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/18218
dc.subjectDisordered Systems and Neural Networks
dc.subjectQuantitative Biology
dc.titleHigher-Order Neutral Networks, Polya Polynomials, and Fermi Cluster Diagrams
dc.typetext

Files

Collections

arXiv