Statistical mechanics of lossy compression using multilayer perceptrons

dc.creatorMimura, Kazushi
dc.creatorOkada, Masato
dc.date2005-08-25
dc.date2006-05-02
dc.date.accessioned2026-07-07T06:41:38Z
dc.date.available2026-07-07T06:41:38Z
dc.descriptionStatistical mechanics is applied to lossy compression using multilayer perceptrons for unbiased Boolean messages. We utilize a tree-like committee machine (committee tree) and tree-like parity machine (parity tree) whose transfer functions are monotonic. For compression using committee tree, a lower bound of achievable distortion becomes small as the number of hidden units K increases. However, it cannot reach the Shannon bound even where K -> infty. For a compression using a parity tree with K >= 2 hidden units, the rate distortion function, which is known as the theoretical limit for compression, is derived where the code length becomes infinity.
dc.description12 pages, 5 figures
dc.identifierhttps://arxiv.org/abs/cond-mat/0508598
dc.identifierhttp://arxiv.org/abs/cond-mat/0508598
dc.identifierPhys. Rev. E, 74, 026108 (2006)
dc.identifierdoi:10.1103/PhysRevE.74.026108
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/101738
dc.subjectStatistical Mechanics
dc.subjectDisordered Systems and Neural Networks
dc.titleStatistical mechanics of lossy compression using multilayer perceptrons
dc.typetext

Files

Collections