Direct classification from compressively sensed images via deep Boltzmann machine

Henry Braun; Pavan Turaga; Andreas Spanias; Cihan Tepedelenlioglu

doi:10.1109/ACSSC.2016.7869080

Direct classification from compressively sensed images via deep Boltzmann machine

Henry Braun, Pavan Turaga, Andreas Spanias, Cihan Tepedelenlioglu

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

6 Scopus citations

Abstract

We examine a potential technique of performing a classification task based on compressively sensed (CS) data, skipping a computationally expensive reconstruction step. A deep Boltzmann machine is trained on a compressive representation of MNIST handwritten digit data, using a random orthoprojector sensing matrix. The network is first pre-trained on uncompressed data in order to learn the structure of the dataset. The outer network layers are then optimized using backpropagation. We find this approach achieves a 1.21% test data error rate at a sensing rate of 0.4, compared to a 0.99% error rate for non-compressive data.

Original language	English (US)
Title of host publication	Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
Editors	Michael B. Matthews
Publisher	IEEE Computer Society
Pages	454-457
Number of pages	4
ISBN (Electronic)	9781538639542
DOIs	https://doi.org/10.1109/ACSSC.2016.7869080
State	Published - Mar 1 2017
Event	50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 - Pacific Grove, United States Duration: Nov 6 2016 → Nov 9 2016

Publication series

Name	Conference Record - Asilomar Conference on Signals, Systems and Computers
ISSN (Print)	1058-6393

Other

Other	50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
Country/Territory	United States
City	Pacific Grove
Period	11/6/16 → 11/9/16

ASJC Scopus subject areas

Signal Processing
Computer Networks and Communications

Access to Document

10.1109/ACSSC.2016.7869080

Cite this

Braun, H., Turaga, P., Spanias, A., & Tepedelenlioglu, C. (2017). Direct classification from compressively sensed images via deep Boltzmann machine. In M. B. Matthews (Ed.), Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 (pp. 454-457). Article 7869080 (Conference Record - Asilomar Conference on Signals, Systems and Computers). IEEE Computer Society. https://doi.org/10.1109/ACSSC.2016.7869080

Direct classification from compressively sensed images via deep Boltzmann machine. / Braun, Henry; Turaga, Pavan ; Spanias, Andreas et al.
Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. ed. / Michael B. Matthews. IEEE Computer Society, 2017. p. 454-457 7869080 (Conference Record - Asilomar Conference on Signals, Systems and Computers).

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

Braun, H, Turaga, P , Spanias, A & Tepedelenlioglu, C 2017, Direct classification from compressively sensed images via deep Boltzmann machine. in MB Matthews (ed.), Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016., 7869080, Conference Record - Asilomar Conference on Signals, Systems and Computers, IEEE Computer Society, pp. 454-457, 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016, Pacific Grove, United States, 11/6/16. https://doi.org/10.1109/ACSSC.2016.7869080

Braun H, Turaga P , Spanias A , Tepedelenlioglu C. Direct classification from compressively sensed images via deep Boltzmann machine. In Matthews MB, editor, Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. IEEE Computer Society. 2017. p. 454-457. 7869080. (Conference Record - Asilomar Conference on Signals, Systems and Computers). doi: 10.1109/ACSSC.2016.7869080

Braun, Henry ; Turaga, Pavan ; Spanias, Andreas et al. / Direct classification from compressively sensed images via deep Boltzmann machine. Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. editor / Michael B. Matthews. IEEE Computer Society, 2017. pp. 454-457 (Conference Record - Asilomar Conference on Signals, Systems and Computers).

@inproceedings{fb1cd3462c1949229332c84cab39a0b0,

title = "Direct classification from compressively sensed images via deep Boltzmann machine",

abstract = "We examine a potential technique of performing a classification task based on compressively sensed (CS) data, skipping a computationally expensive reconstruction step. A deep Boltzmann machine is trained on a compressive representation of MNIST handwritten digit data, using a random orthoprojector sensing matrix. The network is first pre-trained on uncompressed data in order to learn the structure of the dataset. The outer network layers are then optimized using backpropagation. We find this approach achieves a 1.21% test data error rate at a sensing rate of 0.4, compared to a 0.99% error rate for non-compressive data.",

author = "Henry Braun and Pavan Turaga and Andreas Spanias and Cihan Tepedelenlioglu",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 ; Conference date: 06-11-2016 Through 09-11-2016",

year = "2017",

month = mar,

day = "1",

doi = "10.1109/ACSSC.2016.7869080",

language = "English (US)",

series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",

publisher = "IEEE Computer Society",

pages = "454--457",

editor = "Matthews, {Michael B.}",

booktitle = "Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016",

}

TY - GEN

T1 - Direct classification from compressively sensed images via deep Boltzmann machine

AU - Braun, Henry

AU - Turaga, Pavan

AU - Spanias, Andreas

AU - Tepedelenlioglu, Cihan

PY - 2017/3/1

Y1 - 2017/3/1

N2 - We examine a potential technique of performing a classification task based on compressively sensed (CS) data, skipping a computationally expensive reconstruction step. A deep Boltzmann machine is trained on a compressive representation of MNIST handwritten digit data, using a random orthoprojector sensing matrix. The network is first pre-trained on uncompressed data in order to learn the structure of the dataset. The outer network layers are then optimized using backpropagation. We find this approach achieves a 1.21% test data error rate at a sensing rate of 0.4, compared to a 0.99% error rate for non-compressive data.

AB - We examine a potential technique of performing a classification task based on compressively sensed (CS) data, skipping a computationally expensive reconstruction step. A deep Boltzmann machine is trained on a compressive representation of MNIST handwritten digit data, using a random orthoprojector sensing matrix. The network is first pre-trained on uncompressed data in order to learn the structure of the dataset. The outer network layers are then optimized using backpropagation. We find this approach achieves a 1.21% test data error rate at a sensing rate of 0.4, compared to a 0.99% error rate for non-compressive data.

UR - http://www.scopus.com/inward/record.url?scp=85016305376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016305376&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2016.7869080

DO - 10.1109/ACSSC.2016.7869080

M3 - Conference contribution

AN - SCOPUS:85016305376

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 454

EP - 457

BT - Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016

A2 - Matthews, Michael B.

PB - IEEE Computer Society

T2 - 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016

Y2 - 6 November 2016 through 9 November 2016

ER -

Direct classification from compressively sensed images via deep Boltzmann machine

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this