Journal
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
Volume 10, Issue 1, Pages 15-26Publisher
SPRINGER HEIDELBERG
DOI: 10.1007/s13042-017-0694-4
Keywords
Compressive sensing; L1 minimization; Recurrent neural network
Categories
Funding
- National Natural Science Foundation of China [61473325]
Ask authors/readers for more resources
It is significant to solve l1 minimization problems efficiently and reliably in compressed sensing (CS) since the l1 minimization is essential for the recovery of sparse signals. In view of this, a neurodynamic optimization approach is proposed for solving the l1-minimization problems for reconstruction of sparse signals based on a projection neural network (PNN). The proposed neurodynamic optimization approach differs from most l1-solvers in that it operates in continuous time rather than being specified by discrete iterations; i.e., it evolves according to deterministic neurodynamics. The proposed PNN is designed based on subgradient projection methods. The neural network has a simple structure, giving it a potential to be implemented as a large-scale analog circuit. It is proved that under appropriate conditions on the measurement matrix, every neuronal state of the proposed neural network is convergent to the optimal solution of the l1-minimization problem under study. Simulation results are provided to substantiate the effectiveness of the proposed approach.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available