Statistical mechanics of lossy compression using multilayer perceptrons

URI http://harp.lib.hiroshima-u.ac.jp/hiroshima-cu/metadata/4038
File
Title
Statistical mechanics of lossy compression using multilayer perceptrons
Author
氏名 MIMURA Kazushi
ヨミ ミムラ カズシ
別名 三村 和史
氏名 OKADA Masato
ヨミ オカダ マサト
別名 岡田 真人
Abstract

Statistical mechanics is applied to lossy compression using multilayer perceptrons for unbiased Boolean
messages. We utilize a treelike committee machine committee tree and treelike parity machine parity tree
whose transfer functions are monotonic. For compression using a 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→ . 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.

Description Peer Reviewed
Journal Title
Physical Review E - Statistical, Nonlinear, and Soft Matter Physics
Volume
74
Issue
2
Spage
026108-1
Epage
026108-11
Published Date
2006-08
Publisher
American Physical Society
ISSN
1539-3755
NCID
AA11558033
Language
eng
NIIType
Journal Article
Text Version
出版社版
Rights
© 2008 The American Physical Society
Old URI
Set
hiroshima-cu