Skip to main content

Digital-assisted noise-eliminating training for memristor crossbar-based analog neuromorphic computing engine

Publication ,  Conference
Liu, B; Hu, M; Li, H; Mao, ZH; Chen, Y; Huang, T; Zhang, W
Published in: Proceedings - Design Automation Conference
January 1, 2013

The invention of neuromorphic computing architecture is inspired by the working mechanism of human-brain. Memristor technology revitalized neuromorphic computing system design by efficiently executing the analog Matrix-Vector multiplication on the memristor-based crossbar (MBC) structure. However, programming the MBC to the target state can be very challenging due to the difficulty to real-time monitor the memristor state during the training. In this work, we quantitatively analyzed the sensitivity of the MBC programming to the process variations and input signal noise. We then proposed a noise-eliminating training method on top of a new crossbar structure to minimize the noise accumulation during the MBC training and improve the trained system performance, i.e.,the pattern recall rate. A digital-assisted initialization step for MBC training is also introduced to reduce the training failure rate as well as the training time. Experimental results show that our noise-eliminating training method can improve the pattern recall rate. For the tested patterns with 128 × 128 pixels our technique can reduce the MBC training time by 12.6% ∼ 14.1% for the same pattern recognition rate, or improve the pattern recall rate by 18.7% ∼ 36.2% for the same training time. Copyright © 2013 ACM.

Duke Scholars

Published In

Proceedings - Design Automation Conference

DOI

ISSN

0738-100X

ISBN

9781450320719

Publication Date

January 1, 2013
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Liu, B., Hu, M., Li, H., Mao, Z. H., Chen, Y., Huang, T., & Zhang, W. (2013). Digital-assisted noise-eliminating training for memristor crossbar-based analog neuromorphic computing engine. In Proceedings - Design Automation Conference. https://doi.org/10.1145/2463209.2488741
Liu, B., M. Hu, H. Li, Z. H. Mao, Y. Chen, T. Huang, and W. Zhang. “Digital-assisted noise-eliminating training for memristor crossbar-based analog neuromorphic computing engine.” In Proceedings - Design Automation Conference, 2013. https://doi.org/10.1145/2463209.2488741.
Liu B, Hu M, Li H, Mao ZH, Chen Y, Huang T, et al. Digital-assisted noise-eliminating training for memristor crossbar-based analog neuromorphic computing engine. In: Proceedings - Design Automation Conference. 2013.
Liu, B., et al. “Digital-assisted noise-eliminating training for memristor crossbar-based analog neuromorphic computing engine.” Proceedings - Design Automation Conference, 2013. Scopus, doi:10.1145/2463209.2488741.
Liu B, Hu M, Li H, Mao ZH, Chen Y, Huang T, Zhang W. Digital-assisted noise-eliminating training for memristor crossbar-based analog neuromorphic computing engine. Proceedings - Design Automation Conference. 2013.

Published In

Proceedings - Design Automation Conference

DOI

ISSN

0738-100X

ISBN

9781450320719

Publication Date

January 1, 2013