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 languageEnglish (US)
Title of host publicationConference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
PublisherIEEE Computer Society
Pages454-457
Number of pages4
ISBN (Electronic)9781538639542
DOIs
StatePublished - Mar 1 2017
Event50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 - Pacific Grove, United States
Duration: Nov 6 2016Nov 9 2016

Other

Other50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
CountryUnited States
CityPacific Grove
Period11/6/1611/9/16

Fingerprint

Network layers
Backpropagation

ASJC Scopus subject areas

  • Signal Processing
  • Computer Networks and Communications

Cite this

Braun, H., Turaga, P., Spanias, A., & Tepedelenlioglu, C. (2017). Direct classification from compressively sensed images via deep Boltzmann machine. In Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 (pp. 454-457). [7869080] 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; Tepedelenlioglu, Cihan.

Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. IEEE Computer Society, 2017. p. 454-457 7869080.

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

Braun, H, Turaga, P, Spanias, A & Tepedelenlioglu, C 2017, Direct classification from compressively sensed images via deep Boltzmann machine. in Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016., 7869080, 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 Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. IEEE Computer Society. 2017. p. 454-457. 7869080 https://doi.org/10.1109/ACSSC.2016.7869080
Braun, Henry ; Turaga, Pavan ; Spanias, Andreas ; Tepedelenlioglu, Cihan. / Direct classification from compressively sensed images via deep Boltzmann machine. Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. IEEE Computer Society, 2017. pp. 454-457
@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",
year = "2017",
month = "3",
day = "1",
doi = "10.1109/ACSSC.2016.7869080",
language = "English (US)",
pages = "454--457",
booktitle = "Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016",
publisher = "IEEE Computer Society",
address = "United States",

}

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

SP - 454

EP - 457

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

PB - IEEE Computer Society

ER -