Differential Inclusion Neural Network for Compressed Sensing

The issue on neural network method to solve compressed sensing problem is concerned. Combined with optimization technique, nonsmooth analysis theory, differential inclusion theory, and set-valued analysis method, a classical approximate compressed sensing model with dense noise is transformed into a differential inclusion neural network model. On the basis of existence and stable theory, some existence and stability results are also given. Keywords—compressed sensing; differential inclusion theory; nonsmooth analysis; neural network; set-valued analysis

[1]  Qingshan Liu,et al.  A One-Layer Projection Neural Network for Nonsmooth Optimization Subject to Linear Equalities and Bound Constraints , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Qingshan Liu,et al.  $L_{1}$ -Minimization Algorithms for Sparse Signal Reconstruction Based on a Projection Neural Network , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[3]  Julio Jacobo-Berlles,et al.  Face recognition on partially occluded images using compressed sensing , 2014, Pattern Recognit. Lett..

[4]  E.J. Candes,et al.  An Introduction To Compressive Sampling , 2008, IEEE Signal Processing Magazine.

[5]  Michael A. Saunders,et al.  Atomic Decomposition by Basis Pursuit , 1998, SIAM J. Sci. Comput..

[6]  David L Donoho,et al.  Compressed sensing , 2006, IEEE Transactions on Information Theory.

[7]  Zixin Liu,et al.  Neural Network to Solve Concave Games , 2014, Int. J. Comput. Games Technol..

[8]  Balas K. Natarajan,et al.  Sparse Approximate Solutions to Linear Systems , 1995, SIAM J. Comput..

[9]  Jianhong Wu,et al.  Introduction to Functional Differential Equations , 2013 .

[10]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[11]  Jong Chul Ye,et al.  Improved k–t BLAST and k–t SENSE using FOCUSS , 2007, Physics in medicine and biology.