TY - JOUR
T1 - Algorithm Unrolling
T2 - Interpretable, Efficient Deep Learning for Signal and Image Processing
AU - Monga, Vishal
AU - Li, Yuelong
AU - Eldar, Yonina C.
N1 - Publisher Copyright:
© 1991-2012 IEEE.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2021/3
Y1 - 2021/3
N2 - Deep neural networks provide unprecedented performance gains in many real-world problems in signal and image processing. Despite these gains, the future development and practical deployment of deep networks are hindered by their black-box nature, i.e., a lack of interpretability and the need for very large training sets. An emerging technique called algorithm unrolling, or unfolding, offers promise in eliminating these issues by providing a concrete and systematic connection between iterative algorithms that are widely used in signal processing and deep neural networks. Unrolling methods were first proposed to develop fast neural network approximations for sparse coding. More recently, this direction has attracted enormous attention, and it is rapidly growing in both theoretic investigations and practical applications. The increasing popularity of unrolled deep networks is due, in part, to their potential in developing efficient, high-performance (yet interpretable) network architectures from reasonably sized training sets.
AB - Deep neural networks provide unprecedented performance gains in many real-world problems in signal and image processing. Despite these gains, the future development and practical deployment of deep networks are hindered by their black-box nature, i.e., a lack of interpretability and the need for very large training sets. An emerging technique called algorithm unrolling, or unfolding, offers promise in eliminating these issues by providing a concrete and systematic connection between iterative algorithms that are widely used in signal processing and deep neural networks. Unrolling methods were first proposed to develop fast neural network approximations for sparse coding. More recently, this direction has attracted enormous attention, and it is rapidly growing in both theoretic investigations and practical applications. The increasing popularity of unrolled deep networks is due, in part, to their potential in developing efficient, high-performance (yet interpretable) network architectures from reasonably sized training sets.
UR - http://www.scopus.com/inward/record.url?scp=85102034034&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102034034&partnerID=8YFLogxK
U2 - 10.1109/MSP.2020.3016905
DO - 10.1109/MSP.2020.3016905
M3 - Article
AN - SCOPUS:85102034034
VL - 38
SP - 18
EP - 44
JO - IEEE Signal Processing Magazine
JF - IEEE Signal Processing Magazine
SN - 1053-5888
IS - 2
M1 - 9363511
ER -