Titre :

Spiking Sparse Recovery with Non-convex Penalties

Auteur(s) :

Zhang, Xiang [Auteur]
Wuhan University [China]
Yu, Lei [Auteur]
Wuhan University [China]
Zheng, Gang [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Deformable Robots Simulation Team [DEFROST ]
Eldar, Yonina [Auteur]
Weizmann Institute of Science [Rehovot, Israël]

Titre de la revue :

IEEE Transactions on Signal Processing

Pagination :

6272-6285

Éditeur :

Institute of Electrical and Electronics Engineers

Date de publication :

2022

ISSN :

1053-587X

Mot(s)-clé(s) en anglais :

Sparse recovery spiking neural network nonconvex optimization
Sparse recovery
spiking neural network
nonconvex optimization

Discipline(s) HAL :

Informatique [cs]/Traitement du signal et de l'image [eess.SP]

Résumé en anglais : [en]

Sparse recovery (SR) based on spiking neural networks has been shown to be computationally efficient with ultra-low power consumption. However, existing spiking-based sparse recovery (SSR) algorithms are designed for the ...
Lire la suite >Sparse recovery (SR) based on spiking neural networks has been shown to be computationally efficient with ultra-low power consumption. However, existing spiking-based sparse recovery (SSR) algorithms are designed for the convex 1-norm regularized SR problem, which often underestimates the true solution. This paper proposes an adaptive version of SSR, i.e., A-SSR, to optimize a class of non-convex regularized SR problems and analyze its global asymptotic convergence. The superiority of A-SSR is validated with synthetic simulations and real applications, including image reconstruction and face recognition. Furthermore, it is shown that the proposed A-SSR essentially improves the recovery accuracy by avoiding systematic underestimation and obtains over 4 dB PSNR improvement in image reconstruction quality and around 5% improvement in recognition confidence. At the same time, the proposed A-SSR maintains energy efficiency in hardware implementation. When implemented on the neuromorphic Loihi chip, our method consumes only about 1% of the power of the iterative solver FISTA, enabling applications under energy-constrained scenarios.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL