Statistical mechanics of lossy compression for nonmonotonic multilayer perceptrons

Florent Cousseau, Kazushi Mimura, Toshiaki Omori, Masato Okada

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)

Abstract

A lossy data compression scheme for uniformly biased Boolean messages is investigated via statistical mechanics techniques. We utilize a treelike committee machine (committee tree) and a treelike parity machine (parity tree) whose transfer functions are nonmonotonic. 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 Almeida-Thouless stability of the replica symmetric solution is analyzed, and the tuning of the nonmonotonic transfer function is also discussed.

Original languageEnglish
Article number021124
JournalPhysical Review E - Statistical, Nonlinear, and Soft Matter Physics
Volume78
Issue number2
DOIs
Publication statusPublished - 2008 Aug 19

ASJC Scopus subject areas

  • Statistical and Nonlinear Physics
  • Statistics and Probability
  • Condensed Matter Physics

Fingerprint Dive into the research topics of 'Statistical mechanics of lossy compression for nonmonotonic multilayer perceptrons'. Together they form a unique fingerprint.

Cite this