TY - JOUR
T1 - Low power sparse approximation on reconfigurable analog hardware
AU - Shapero, Samuel
AU - Charles, Adam S.
AU - Rozell, Christopher J.
AU - Hasler, Paul
N1 - Funding Information:
Manuscript received February 21, 2012; revised June 20, 2012; accepted July 28, 2012. Date of publication September 27, 2012; date of current version December 05, 2012. This work was supported in part by the National Science Foundation (NSF) under Grant CCF-0905346. Preliminary versions of portions of this work were presented at the 2010 ASILOMAR Conference on Signals, Systems, and Computers and the 2011 IEEE Biomedical Circuits and Systems Conference. This paper was recommended by Guest Editor G. Setti.
PY - 2012
Y1 - 2012
N2 - Compressed sensing is an important application in signal and image processing which requires solving nonlinear optimization problems. A Hopfield-Network-like analog system is proposed as a solution, using the locally competitive algorithm (LCA) to solve an overcomplete ell1 sparse approximation problem. A scalable system architecture using sub-threshold currents is described, including vector matrix multipliers (VMMs) and a nonlinear thresholder. A 4 × 6 nonlinear system is implemented on the RASP 2.9v chip, a field programmable analog array with directly programmable floating gate elements, allowing highly accurate VMMs. The circuit successfully reproduced the outputs of a digital optimization program, converging to within 4.8% rms, and an objective value only 1.3% higher on average. The active circuit consumed 29 μ A of current at 2.4 V, and converges on solutions in 240 μ s. A smaller 2 × 3 system is also implemented. Extrapolating the scaling trends to a N=1000 node system, the analog LCA compares favorably with state-of-the-art digital solutions, using a small fraction of the power to arrive at solutions ten times faster. Finally, we provide simulations of large scale systems to show the behavior of the system scaled to nontrivial problem sizes.
AB - Compressed sensing is an important application in signal and image processing which requires solving nonlinear optimization problems. A Hopfield-Network-like analog system is proposed as a solution, using the locally competitive algorithm (LCA) to solve an overcomplete ell1 sparse approximation problem. A scalable system architecture using sub-threshold currents is described, including vector matrix multipliers (VMMs) and a nonlinear thresholder. A 4 × 6 nonlinear system is implemented on the RASP 2.9v chip, a field programmable analog array with directly programmable floating gate elements, allowing highly accurate VMMs. The circuit successfully reproduced the outputs of a digital optimization program, converging to within 4.8% rms, and an objective value only 1.3% higher on average. The active circuit consumed 29 μ A of current at 2.4 V, and converges on solutions in 240 μ s. A smaller 2 × 3 system is also implemented. Extrapolating the scaling trends to a N=1000 node system, the analog LCA compares favorably with state-of-the-art digital solutions, using a small fraction of the power to arrive at solutions ten times faster. Finally, we provide simulations of large scale systems to show the behavior of the system scaled to nontrivial problem sizes.
KW - Compressed sensing
KW - Hopfield neural networks
KW - convex optimization
KW - field programmable analog arrays
UR - http://www.scopus.com/inward/record.url?scp=84870987359&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84870987359&partnerID=8YFLogxK
U2 - 10.1109/JETCAS.2012.2214615
DO - 10.1109/JETCAS.2012.2214615
M3 - Article
AN - SCOPUS:84870987359
SN - 2156-3357
VL - 2
SP - 530
EP - 541
JO - IEEE Journal on Emerging and Selected Topics in Circuits and Systems
JF - IEEE Journal on Emerging and Selected Topics in Circuits and Systems
IS - 3
M1 - 6313932
ER -