A Collaborative Neurodynamic Approach to Sparse Coding

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

5 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Title of host publicationAdvances in Neural Networks – ISNN 2019
Subtitle of host publicationProceedings, Part I
EditorsHuchuan Lu, Huajin Tang, Zhanshan Wang
PublisherSpringer Nature Switzerland AG
Pages454-462
ISBN (Electronic)9783030227968
ISBN (Print)9783030227951
Publication statusPublished - Jul 2019

Publication series

NameLecture Notes in Computer Science
Volume11554
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Title16th International Symposium on Neural Networks (ISNN 2019)
LocationHypercube
PlaceRussian Federation
CityMoscow
Period10 - 12 July 2019

Abstract

In this paper, a collaborative neurodynamic approach is proposed for sparse coding. As the formulated sparse coding optimization problem with l0-norm objective function is NP-hard, it is reformulated as a global optimization problem based on an inverted Gaussian function. A group of neurodynamic optimization models is employed to solve the reformulated problem by gradually decreasing the value of the parameter of the inverted Gaussian function. The experimental results show the superior performance of the proposed approach.

Research Area(s)

  • Collaborative neurodynamic optimization, Signal reconstruction, Sparse coding

Citation Format(s)

A Collaborative Neurodynamic Approach to Sparse Coding. / Che, Hangjun; Wang, Jun; Zhang, Wei.

Advances in Neural Networks – ISNN 2019: Proceedings, Part I. ed. / Huchuan Lu; Huajin Tang; Zhanshan Wang. Springer Nature Switzerland AG, 2019. p. 454-462 (Lecture Notes in Computer Science; Vol. 11554).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review