A continuous-time recurrent neural network for sparse signal reconstruction via ℓ<inf>1</inf> minimization

Yan, Z; Le, X; Wen, S; Lu, J

A continuous-time recurrent neural network for sparse signal reconstruction via ℓ<inf>1</inf> minimization

Yan, Z

Le, X Wen, S Lu, J

Permalink

Publication Type:: Conference Proceeding
Citation:: 8th International Conference on Information Science and Technology, ICIST 2018, 2018, pp. 43 - 49
Issue Date:: 2018-08-06

Closed Access

	Filename	Description	Size
	A Continuous Time Recurrent Neural Network.pdf	Published version	368.49 kB		View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Yan, Z https://orcid.org/0000-0003-3368-2100	en_US
dc.contributor.author	Le, X	en_US
dc.contributor.author	Wen, S	en_US
dc.contributor.author	Lu, J https://orcid.org/0000-0003-0690-4732	en_US
dc.date.issued	2018-08-06	en_US
dc.identifier.citation	8th International Conference on Information Science and Technology, ICIST 2018, 2018, pp. 43 - 49	en_US
dc.identifier.isbn	9781538637814	en_US
dc.identifier.uri	http://hdl.handle.net/10453/128517
dc.description.abstract	© 2018 IEEE. This paper presents a neurodynamic model for solving e1 minimization problems for sparse signal reconstruction. The essence of the proposed approach lies in its capability to operate in continuous time, which enables it to outperform most existing iterative e1-solvers in dynamic environments. The model is described by a goal-seeking recurrent neural network and it evolves according to its deterministic neurodynamics. It is proved that the model globally converges to the optimal solution to the e1-minimization problem under study. The connection weights of the neural network model are determined by using subgradient projection methods and the activation function is designed based on subdifferential. Due to its simple structure, the hardware implementation of this neurodynamic model is viable and cost-effective, which sheds light on real-time sparse signal recovery via large scale e1 minimization formulations.	en_US
dc.relation.ispartof	8th International Conference on Information Science and Technology, ICIST 2018	en_US
dc.relation.isbasedon	10.1109/ICIST.2018.8426132	en_US
dc.title	A continuous-time recurrent neural network for sparse signal reconstruction via ℓ<inf>1</inf> minimization	en_US
dc.type	Conference Proceeding
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

© 2018 IEEE. This paper presents a neurodynamic model for solving e1 minimization problems for sparse signal reconstruction. The essence of the proposed approach lies in its capability to operate in continuous time, which enables it to outperform most existing iterative e1-solvers in dynamic environments. The model is described by a goal-seeking recurrent neural network and it evolves according to its deterministic neurodynamics. It is proved that the model globally converges to the optimal solution to the e1-minimization problem under study. The connection weights of the neural network model are determined by using subgradient projection methods and the activation function is designed based on subdifferential. Due to its simple structure, the hardware implementation of this neurodynamic model is viable and cost-effective, which sheds light on real-time sparse signal recovery via large scale e1 minimization formulations.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/128517