Skip to main content

A closed-loop design to enhance weight stability of memristor based neural network chips

Publication ,  Conference
Yan, B; Yang, J; Wu, Q; Chen, Y; Li, H
Published in: IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
December 13, 2017

Compared with the algorithm optimizations, brain-inspired neural network chips aim to fundamentally change the computer architecture and therefore enhance the computation capability and performance in advanced data processing. In recent years, memristor technology has been investigated in developing high-speed and large-capacity neural network chips. However, it has been observed that memristance values that represent the well-trained network weights can be disturbed by electrical or thermal perturbations. It severely degrades overall system reliability and emerges as a major design challenge. In this work, we systematically analyze the impacts of low-voltage induced memristance drift upon weight disturbance after times of recall operations. A closed-loop design by introducing a real-time feedback controller is proposed to enhance the weight stability of memristor based neural network chips. By mimicking the training process, the controller adaptively compensates the memristance deviation, according to the relation of the input data and recall output. In view of tiny disturbance per access, we integrate the memristance compensation into regular recall operation to avoid the execution speed degradation. Our simulations based on the implementation of representative single-layer (two-layer) network show that the proposed closed-loop design can prolong the service time of memristor-based neural network chip by 14.85x (14.94x), without reducing computational speed. Extra circuitry of the feedback controller induces a negligible overhead about 1.16% on overall power consumption.

Duke Scholars

Published In

IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD

DOI

ISSN

1092-3152

ISBN

9781538630938

Publication Date

December 13, 2017

Volume

2017-November

Start / End Page

541 / 548
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Yan, B., Yang, J., Wu, Q., Chen, Y., & Li, H. (2017). A closed-loop design to enhance weight stability of memristor based neural network chips. In IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD (Vol. 2017-November, pp. 541–548). https://doi.org/10.1109/ICCAD.2017.8203824
Yan, B., J. Yang, Q. Wu, Y. Chen, and H. Li. “A closed-loop design to enhance weight stability of memristor based neural network chips.” In IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD, 2017-November:541–48, 2017. https://doi.org/10.1109/ICCAD.2017.8203824.
Yan B, Yang J, Wu Q, Chen Y, Li H. A closed-loop design to enhance weight stability of memristor based neural network chips. In: IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD. 2017. p. 541–8.
Yan, B., et al. “A closed-loop design to enhance weight stability of memristor based neural network chips.” IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD, vol. 2017-November, 2017, pp. 541–48. Scopus, doi:10.1109/ICCAD.2017.8203824.
Yan B, Yang J, Wu Q, Chen Y, Li H. A closed-loop design to enhance weight stability of memristor based neural network chips. IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD. 2017. p. 541–548.

Published In

IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD

DOI

ISSN

1092-3152

ISBN

9781538630938

Publication Date

December 13, 2017

Volume

2017-November

Start / End Page

541 / 548