Statistical mechanics of lossy compression for non-monotonic multilayer perceptrons

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

A lossy data compression scheme for uniformly biased Boolean messages is investigated via statistical mechanics techniques. We utilize tree-like committee machine (committee tree) and tree-like parity machine (parity tree) whose transfer functions are non-monotonic. The scheme performance at the infinite code length limit is analyzed using the replica method. Both committee and parity treelike networks are shown to saturate the Shannon bound. The AT stability of the Replica Symmetric solution is analyzed, and the tuning of the non-monotonic transfer function is also discussed.
29 pages, 7 figures

Keywords

Statistical Mechanics, Disordered Systems and Neural Networks, Information Theory

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/167697

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/0807.4009
 http://arxiv.org/abs/0807.4009
 Phys. Rev. E, 78, 021124 (2008)
 doi:10.1103/PhysRevE.78.021124

Collections

arXiv