Interacting neural networks and cryptography

Simple item page
dc.creatorKinzel, Wolfgang
dc.creatorKanter, Ido
dc.date2002-03-01
dc.date.accessioned2026-07-07T02:44:34Z
dc.date.available2026-07-07T02:44:34Z
dc.descriptionTwo neural networks which are trained on their mutual output bits are analysed using methods of statistical physics. The exact solution of the dynamics of the two weight vectors shows a novel phenomenon: The networks synchronize to a state with identical time dependent weights. Extending the models to multilayer networks with discrete weights, it is shown how synchronization by mutual learning can be applied to secret key exchange over a public channel.
dc.descriptionInvited talk for the meeting of the German Physical Society
dc.identifierhttps://arxiv.org/abs/cond-mat/0203011
dc.identifierhttp://arxiv.org/abs/cond-mat/0203011
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/18980
dc.subjectDisordered Systems and Neural Networks
dc.titleInteracting neural networks and cryptography
dc.typetext

Files

Collections

arXiv