Features as sufficient statistics

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

An image is often represented by a set of detected features. We get an enormous compression by representing images in this way. Furthermore, we get a representation which is little affected by small amounts of noise in the image. However, features are typically chosen in an ad hoc manner. We show how a good set of features can be obtained using sufficient statistics. The idea of sparse data representation naturally arises. We treat the 1-dimensional and 2-dimensional signal reconstruction problem to make our ideas concrete.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997
PublisherNeural information processing systems foundation
Pages794-800
Number of pages7
ISBN (Print)0262100762, 9780262100762
StatePublished - 1998
Event11th Annual Conference on Neural Information Processing Systems, NIPS 1997 - Denver, CO, United States
Duration: Dec 1 1997Dec 6 1997

Other

Other11th Annual Conference on Neural Information Processing Systems, NIPS 1997
CountryUnited States
CityDenver, CO
Period12/1/9712/6/97

Fingerprint

Signal reconstruction
Statistics
Concretes

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Geiger, D., Rudra, A., & Maloney, L. (1998). Features as sufficient statistics. In Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997 (pp. 794-800). Neural information processing systems foundation.

Features as sufficient statistics. / Geiger, D.; Rudra, A.; Maloney, L.

Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997. Neural information processing systems foundation, 1998. p. 794-800.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Geiger, D, Rudra, A & Maloney, L 1998, Features as sufficient statistics. in Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997. Neural information processing systems foundation, pp. 794-800, 11th Annual Conference on Neural Information Processing Systems, NIPS 1997, Denver, CO, United States, 12/1/97.
Geiger D, Rudra A, Maloney L. Features as sufficient statistics. In Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997. Neural information processing systems foundation. 1998. p. 794-800
Geiger, D. ; Rudra, A. ; Maloney, L. / Features as sufficient statistics. Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997. Neural information processing systems foundation, 1998. pp. 794-800
@inproceedings{4cba72dbf8f64b8eb15494925b3f43d2,
title = "Features as sufficient statistics",
abstract = "An image is often represented by a set of detected features. We get an enormous compression by representing images in this way. Furthermore, we get a representation which is little affected by small amounts of noise in the image. However, features are typically chosen in an ad hoc manner. We show how a good set of features can be obtained using sufficient statistics. The idea of sparse data representation naturally arises. We treat the 1-dimensional and 2-dimensional signal reconstruction problem to make our ideas concrete.",
author = "D. Geiger and A. Rudra and L. Maloney",
year = "1998",
language = "English (US)",
isbn = "0262100762",
pages = "794--800",
booktitle = "Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997",
publisher = "Neural information processing systems foundation",

}

TY - GEN

T1 - Features as sufficient statistics

AU - Geiger, D.

AU - Rudra, A.

AU - Maloney, L.

PY - 1998

Y1 - 1998

N2 - An image is often represented by a set of detected features. We get an enormous compression by representing images in this way. Furthermore, we get a representation which is little affected by small amounts of noise in the image. However, features are typically chosen in an ad hoc manner. We show how a good set of features can be obtained using sufficient statistics. The idea of sparse data representation naturally arises. We treat the 1-dimensional and 2-dimensional signal reconstruction problem to make our ideas concrete.

AB - An image is often represented by a set of detected features. We get an enormous compression by representing images in this way. Furthermore, we get a representation which is little affected by small amounts of noise in the image. However, features are typically chosen in an ad hoc manner. We show how a good set of features can be obtained using sufficient statistics. The idea of sparse data representation naturally arises. We treat the 1-dimensional and 2-dimensional signal reconstruction problem to make our ideas concrete.

UR - http://www.scopus.com/inward/record.url?scp=84890477319&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890477319&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0262100762

SN - 9780262100762

SP - 794

EP - 800

BT - Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997

PB - Neural information processing systems foundation

ER -