Skip to main content
Journal cover image

Small-world Hopfield neural networks with weight salience priority and memristor synapses for digit recognition

Publication ,  Journal Article
Duan, S; Dong, Z; Hu, X; Wang, L; Li, H
Published in: Neural Computing and Applications
May 1, 2016

A novel systematic design of associative memory networks is addressed in this paper, by incorporating both the biological small-world effect and the recently acclaimed memristor into the conventional Hopfield neural network. More specifically, the original fully connected Hopfield network is diluted by considering the small-world effect, based on a preferential connection removal criteria, i.e., weight salience priority. The generated sparse network exhibits comparable performance in associative memory but with much less connections. Furthermore, a hardware implementation scheme of the small-world Hopfield network is proposed using the experimental threshold adaptive memristor (TEAM) synaptic-based circuits. Finally, performance of the proposed network is validated by illustrative examples of digit recognition.

Duke Scholars

Published In

Neural Computing and Applications

DOI

ISSN

0941-0643

Publication Date

May 1, 2016

Volume

27

Issue

4

Start / End Page

837 / 844

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 4611 Machine learning
  • 4603 Computer vision and multimedia computation
  • 4602 Artificial intelligence
  • 1702 Cognitive Sciences
  • 0906 Electrical and Electronic Engineering
  • 0801 Artificial Intelligence and Image Processing
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Duan, S., Dong, Z., Hu, X., Wang, L., & Li, H. (2016). Small-world Hopfield neural networks with weight salience priority and memristor synapses for digit recognition. Neural Computing and Applications, 27(4), 837–844. https://doi.org/10.1007/s00521-015-1899-7
Duan, S., Z. Dong, X. Hu, L. Wang, and H. Li. “Small-world Hopfield neural networks with weight salience priority and memristor synapses for digit recognition.” Neural Computing and Applications 27, no. 4 (May 1, 2016): 837–44. https://doi.org/10.1007/s00521-015-1899-7.
Duan S, Dong Z, Hu X, Wang L, Li H. Small-world Hopfield neural networks with weight salience priority and memristor synapses for digit recognition. Neural Computing and Applications. 2016 May 1;27(4):837–44.
Duan, S., et al. “Small-world Hopfield neural networks with weight salience priority and memristor synapses for digit recognition.” Neural Computing and Applications, vol. 27, no. 4, May 2016, pp. 837–44. Scopus, doi:10.1007/s00521-015-1899-7.
Duan S, Dong Z, Hu X, Wang L, Li H. Small-world Hopfield neural networks with weight salience priority and memristor synapses for digit recognition. Neural Computing and Applications. 2016 May 1;27(4):837–844.
Journal cover image

Published In

Neural Computing and Applications

DOI

ISSN

0941-0643

Publication Date

May 1, 2016

Volume

27

Issue

4

Start / End Page

837 / 844

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 4611 Machine learning
  • 4603 Computer vision and multimedia computation
  • 4602 Artificial intelligence
  • 1702 Cognitive Sciences
  • 0906 Electrical and Electronic Engineering
  • 0801 Artificial Intelligence and Image Processing