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
N1 - Publisher Copyright:
© 2016 IEEE.
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 -