Achievable rates for pattern recognition: Binary and Gaussian cases

M. Brandon Westover; Joseph A. O'Sullivan

doi:10.1109/ISIT.2005.1523286

Achievable rates for pattern recognition: Binary and Gaussian cases

M. Brandon Westover
, Joseph A. O'Sullivan

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

Recently we presented information-theoretic bounds for the achievable rates of pattern recognition systems operating under data compression constraints. In this paper we improve on our previous inner bound, and report progress toward finding formulas for the achievable rate region boundaries in the special cases where the pattern data is either binary or Gaussian.

Original language	English
Title of host publication	Proceedings of the 2005 IEEE International Symposium on Information Theory, ISIT 05
Pages	28-32
Number of pages	5
DOIs	https://doi.org/10.1109/ISIT.2005.1523286
State	Published - 2005
Event	2005 IEEE International Symposium on Information Theory, ISIT 05 - Adelaide, Australia Duration: Sep 4 2005 → Sep 9 2005

Publication series

Name	IEEE International Symposium on Information Theory - Proceedings
Volume	2005
ISSN (Print)	2157-8099

Conference

Conference	2005 IEEE International Symposium on Information Theory, ISIT 05
Country/Territory	Australia
City	Adelaide
Period	09/4/05 → 09/9/05

Access to Document

10.1109/ISIT.2005.1523286

Cite this

@inproceedings{15f4a75b06a64006a5b8f381274ca17c,

title = "Achievable rates for pattern recognition: Binary and Gaussian cases",

abstract = "Recently we presented information-theoretic bounds for the achievable rates of pattern recognition systems operating under data compression constraints. In this paper we improve on our previous inner bound, and report progress toward finding formulas for the achievable rate region boundaries in the special cases where the pattern data is either binary or Gaussian.",

author = "Westover, \{M. Brandon\} and O'Sullivan, \{Joseph A.\}",

year = "2005",

doi = "10.1109/ISIT.2005.1523286",

language = "English",

isbn = "0780391519",

series = "IEEE International Symposium on Information Theory - Proceedings",

pages = "28--32",

booktitle = "Proceedings of the 2005 IEEE International Symposium on Information Theory, ISIT 05",

note = "2005 IEEE International Symposium on Information Theory, ISIT 05 ; Conference date: 04-09-2005 Through 09-09-2005",

}

Westover, MB & O'Sullivan, JA 2005, Achievable rates for pattern recognition: Binary and Gaussian cases. in Proceedings of the 2005 IEEE International Symposium on Information Theory, ISIT 05., 1523286, IEEE International Symposium on Information Theory - Proceedings, vol. 2005, pp. 28-32, 2005 IEEE International Symposium on Information Theory, ISIT 05, Adelaide, Australia, 09/4/05. https://doi.org/10.1109/ISIT.2005.1523286

Achievable rates for pattern recognition: Binary and Gaussian cases. / Westover, M. Brandon; O'Sullivan, Joseph A.
Proceedings of the 2005 IEEE International Symposium on Information Theory, ISIT 05. 2005. p. 28-32 1523286 (IEEE International Symposium on Information Theory - Proceedings; Vol. 2005).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Achievable rates for pattern recognition

T2 - 2005 IEEE International Symposium on Information Theory, ISIT 05

AU - Westover, M. Brandon

AU - O'Sullivan, Joseph A.

PY - 2005

Y1 - 2005

N2 - Recently we presented information-theoretic bounds for the achievable rates of pattern recognition systems operating under data compression constraints. In this paper we improve on our previous inner bound, and report progress toward finding formulas for the achievable rate region boundaries in the special cases where the pattern data is either binary or Gaussian.

AB - Recently we presented information-theoretic bounds for the achievable rates of pattern recognition systems operating under data compression constraints. In this paper we improve on our previous inner bound, and report progress toward finding formulas for the achievable rate region boundaries in the special cases where the pattern data is either binary or Gaussian.

UR - https://www.scopus.com/pages/publications/33749436100

U2 - 10.1109/ISIT.2005.1523286

DO - 10.1109/ISIT.2005.1523286

M3 - Conference contribution

AN - SCOPUS:33749436100

SN - 0780391519

SN - 9780780391512

T3 - IEEE International Symposium on Information Theory - Proceedings

SP - 28

EP - 32

BT - Proceedings of the 2005 IEEE International Symposium on Information Theory, ISIT 05

Y2 - 4 September 2005 through 9 September 2005

ER -

Achievable rates for pattern recognition: Binary and Gaussian cases

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this