ホサカ　タダアキ   HOSAKA TADAAKI   保坂　忠明    所属   明治大学  理工学部    職種   専任准教授
言語種別	英語
発行・発表の年月	2006/06
形態種別	学術雑誌
査読	査読あり
標題	Statistical mechanical approach to lossy data compression: Theory and practice
執筆形態	共著(筆頭者)
掲載誌名	PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
掲載区分	国外
出版社・発行元	ELSEVIER SCIENCE BV
巻・号・頁	365(1),pp.113-119
著者・共著者	T Hosaka,Y Kabashima
概要	The encoder and decoder for lossy data compression of binary memoryless sources are developed on the basis of a specific-type nonmonotonic perceptron. Statistical mechanical analysis indicates that the potential ability of the perceptron-based code saturates the theoretically achievable limit in most cases although exactly performing the compression is computationally difficult. To resolve this difficulty, we provide a computationally tractable approximation algorithm using belief propagation (BP), which is a current standard algorithm of probabilistic inference. Introducing several approximations and heuristics, the BP-based algorithm exhibits performance that is close to the achievable limit in a practical time scale in optimal cases. (c) 2006 Elsevier B.V. All rights reserved.
DOI	10.1016/j.physa.2006.01.013
ISSN	0378-4371