A quantization-aware regularized learning method in multilevel memristor-based neuromorphic computing system
Publication
, Conference
Song, C; Liu, B; Wen, W; Li, H; Chen, Y
Published in: NVMSA 2017 - 6th IEEE Non-Volatile Memory Systems and Applications Symposium
October 10, 2017
In this work, we propose a regularized learning method that is able to take into account the deviation of the memristor-mapped synaptic weights from the target values determined during the training process. Experimental results obtained when utilizing the MNIST data set show that compared to the conventional learning method which considers the learning and mapping processes separately, our learning method can substantially improve the computation accuracy of the mapped two-layer multilayer perceptron (and LeNet-5) on multi-level memristor crossbars by 4.30% (11.05%) for binary representation, and by 0.40% (8.06%) for three-level representation.
Duke Scholars
Published In
NVMSA 2017 - 6th IEEE Non-Volatile Memory Systems and Applications Symposium
DOI
Publication Date
October 10, 2017
Citation
APA
Chicago
ICMJE
MLA
NLM
Song, C., Liu, B., Wen, W., Li, H., & Chen, Y. (2017). A quantization-aware regularized learning method in multilevel memristor-based neuromorphic computing system. In NVMSA 2017 - 6th IEEE Non-Volatile Memory Systems and Applications Symposium. https://doi.org/10.1109/NVMSA.2017.8064465
Song, C., B. Liu, W. Wen, H. Li, and Y. Chen. “A quantization-aware regularized learning method in multilevel memristor-based neuromorphic computing system.” In NVMSA 2017 - 6th IEEE Non-Volatile Memory Systems and Applications Symposium, 2017. https://doi.org/10.1109/NVMSA.2017.8064465.
Song C, Liu B, Wen W, Li H, Chen Y. A quantization-aware regularized learning method in multilevel memristor-based neuromorphic computing system. In: NVMSA 2017 - 6th IEEE Non-Volatile Memory Systems and Applications Symposium. 2017.
Song, C., et al. “A quantization-aware regularized learning method in multilevel memristor-based neuromorphic computing system.” NVMSA 2017 - 6th IEEE Non-Volatile Memory Systems and Applications Symposium, 2017. Scopus, doi:10.1109/NVMSA.2017.8064465.
Song C, Liu B, Wen W, Li H, Chen Y. A quantization-aware regularized learning method in multilevel memristor-based neuromorphic computing system. NVMSA 2017 - 6th IEEE Non-Volatile Memory Systems and Applications Symposium. 2017.
Published In
NVMSA 2017 - 6th IEEE Non-Volatile Memory Systems and Applications Symposium
DOI
Publication Date
October 10, 2017