Skip to main content
Journal cover image

Forgetting memristor based neuromorphic system for pattern training and recognition

Publication ,  Journal Article
Zhang, P; Li, C; Huang, T; Chen, L; Chen, Y
Published in: Neurocomputing
January 26, 2017

This paper presents a neuromorphic system for mean variance based pattern training and recognition. The system contains a self-learning circuit, a training circuit and a recognition circuit. Memristor model with forgetting effect which has memory ability and forgetting effect simultaneously is applied to simulate forgetting mechanism of neuromorphic system. Different from previous work, which divided training circuit as off line process, here the weight-changing circuit and the recognition part are combined on line for pattern training and recognition. For illustration, the whole neuromorphic system is applied to recognize handwriting number ‘0–9’ on gray images, and simulations verify its effectiveness.

Duke Scholars

Published In

Neurocomputing

DOI

EISSN

1872-8286

ISSN

0925-2312

Publication Date

January 26, 2017

Volume

222

Start / End Page

47 / 53

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 52 Psychology
  • 46 Information and computing sciences
  • 40 Engineering
  • 17 Psychology and Cognitive Sciences
  • 09 Engineering
  • 08 Information and Computing Sciences
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Zhang, P., Li, C., Huang, T., Chen, L., & Chen, Y. (2017). Forgetting memristor based neuromorphic system for pattern training and recognition. Neurocomputing, 222, 47–53. https://doi.org/10.1016/j.neucom.2016.10.012
Zhang, P., C. Li, T. Huang, L. Chen, and Y. Chen. “Forgetting memristor based neuromorphic system for pattern training and recognition.” Neurocomputing 222 (January 26, 2017): 47–53. https://doi.org/10.1016/j.neucom.2016.10.012.
Zhang P, Li C, Huang T, Chen L, Chen Y. Forgetting memristor based neuromorphic system for pattern training and recognition. Neurocomputing. 2017 Jan 26;222:47–53.
Zhang, P., et al. “Forgetting memristor based neuromorphic system for pattern training and recognition.” Neurocomputing, vol. 222, Jan. 2017, pp. 47–53. Scopus, doi:10.1016/j.neucom.2016.10.012.
Zhang P, Li C, Huang T, Chen L, Chen Y. Forgetting memristor based neuromorphic system for pattern training and recognition. Neurocomputing. 2017 Jan 26;222:47–53.
Journal cover image

Published In

Neurocomputing

DOI

EISSN

1872-8286

ISSN

0925-2312

Publication Date

January 26, 2017

Volume

222

Start / End Page

47 / 53

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 52 Psychology
  • 46 Information and computing sciences
  • 40 Engineering
  • 17 Psychology and Cognitive Sciences
  • 09 Engineering
  • 08 Information and Computing Sciences