DeepCodec: Adaptive sensing and recovery via deep convolutional neural networks

Ali Mousavi; Gautam Dasarathy; Richard G. Baraniuk

doi:10.1109/ALLERTON.2017.8262812

DeepCodec: Adaptive sensing and recovery via deep convolutional neural networks

Ali Mousavi, Gautam Dasarathy, Richard G. Baraniuk

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

39 Scopus citations

Abstract

We develop a novel computational sensing framework for sensing and recovering structured signals. When trained on a set of representative signals, our framework learns to take undersampled measurements and recover signals from these measurements using a deep convolutional neural network. In other words, it learns a transformation from the original signals to a near-optimal number of undersampled measurements and the inverse transformation from measurements to signals. This is in contrast to conventional compressive sensing (CS) systems that use random linear measurements and convex optimization or iterative algorithms for signal recovery.

Original language	English (US)
Title of host publication	55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	744
Number of pages	1
ISBN (Electronic)	9781538632666
DOIs	https://doi.org/10.1109/ALLERTON.2017.8262812
State	Published - Jul 1 2017
Externally published	Yes
Event	55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017 - Monticello, United States Duration: Oct 3 2017 → Oct 6 2017

Publication series

Name	55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017
Volume	2018-January

Other

Other	55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017
Country/Territory	United States
City	Monticello
Period	10/3/17 → 10/6/17

ASJC Scopus subject areas

Computer Networks and Communications
Hardware and Architecture
Signal Processing
Energy Engineering and Power Technology
Control and Optimization

Access to Document

10.1109/ALLERTON.2017.8262812

Cite this

Mousavi, A., Dasarathy, G., & Baraniuk, R. G. (2017). DeepCodec: Adaptive sensing and recovery via deep convolutional neural networks. In 55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017 (pp. 744). (55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ALLERTON.2017.8262812

DeepCodec: Adaptive sensing and recovery via deep convolutional neural networks. / Mousavi, Ali; Dasarathy, Gautam; Baraniuk, Richard G.
55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 744 (55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017; Vol. 2018-January).

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

Mousavi, A, Dasarathy, G & Baraniuk, RG 2017, DeepCodec: Adaptive sensing and recovery via deep convolutional neural networks. in 55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017. 55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 744, 55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017, Monticello, United States, 10/3/17. https://doi.org/10.1109/ALLERTON.2017.8262812

Mousavi A, Dasarathy G, Baraniuk RG. DeepCodec: Adaptive sensing and recovery via deep convolutional neural networks. In 55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 744. (55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017). doi: 10.1109/ALLERTON.2017.8262812

Mousavi, Ali ; Dasarathy, Gautam ; Baraniuk, Richard G. / DeepCodec : Adaptive sensing and recovery via deep convolutional neural networks. 55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 744 (55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017).

@inproceedings{f810e8723f32444e8b2de697476c61dc,

title = "DeepCodec: Adaptive sensing and recovery via deep convolutional neural networks",

abstract = "We develop a novel computational sensing framework for sensing and recovering structured signals. When trained on a set of representative signals, our framework learns to take undersampled measurements and recover signals from these measurements using a deep convolutional neural network. In other words, it learns a transformation from the original signals to a near-optimal number of undersampled measurements and the inverse transformation from measurements to signals. This is in contrast to conventional compressive sensing (CS) systems that use random linear measurements and convex optimization or iterative algorithms for signal recovery.",

author = "Ali Mousavi and Gautam Dasarathy and Baraniuk, {Richard G.}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017 ; Conference date: 03-10-2017 Through 06-10-2017",

year = "2017",

month = jul,

day = "1",

doi = "10.1109/ALLERTON.2017.8262812",

language = "English (US)",

series = "55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "744",

booktitle = "55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017",

}

TY - GEN

T1 - DeepCodec

T2 - 55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017

AU - Mousavi, Ali

AU - Dasarathy, Gautam

AU - Baraniuk, Richard G.

PY - 2017/7/1

Y1 - 2017/7/1

N2 - We develop a novel computational sensing framework for sensing and recovering structured signals. When trained on a set of representative signals, our framework learns to take undersampled measurements and recover signals from these measurements using a deep convolutional neural network. In other words, it learns a transformation from the original signals to a near-optimal number of undersampled measurements and the inverse transformation from measurements to signals. This is in contrast to conventional compressive sensing (CS) systems that use random linear measurements and convex optimization or iterative algorithms for signal recovery.

AB - We develop a novel computational sensing framework for sensing and recovering structured signals. When trained on a set of representative signals, our framework learns to take undersampled measurements and recover signals from these measurements using a deep convolutional neural network. In other words, it learns a transformation from the original signals to a near-optimal number of undersampled measurements and the inverse transformation from measurements to signals. This is in contrast to conventional compressive sensing (CS) systems that use random linear measurements and convex optimization or iterative algorithms for signal recovery.

UR - http://www.scopus.com/inward/record.url?scp=85047966244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047966244&partnerID=8YFLogxK

U2 - 10.1109/ALLERTON.2017.8262812

DO - 10.1109/ALLERTON.2017.8262812

M3 - Conference contribution

AN - SCOPUS:85047966244

T3 - 55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017

SP - 744

BT - 55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 3 October 2017 through 6 October 2017

ER -

DeepCodec: Adaptive sensing and recovery via deep convolutional neural networks

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this