A Multifault‐Tolerant Training Scheme for Nonideal Memristive Neural Networks
Memristor crossbar is extensively investigated as an energy‐efficient accelerator for neural network (NN) computations. However, hardware implementation of NNs using realistic memristors is challenging due to the ubiquity of faults (mainly classified into hard and soft faults) in memristors. Herein,...
Автори: | Yihong Chen, Zhen Fan, Shuai Dong, Minghui Qin, Min Zeng, Xubing Lu, Gougu Zhou, Xingsen Gao, Jun-Ming Liu |
---|---|
Формат: | Стаття |
Мова: | English |
Опубліковано: |
Wiley
2022-05-01
|
Серія: | Advanced Intelligent Systems |
Предмети: | |
Онлайн доступ: | https://doi.org/10.1002/aisy.202100237 |
Схожі ресурси
-
Comments on Pinched Hysteresis Loops of Memristive Elements
за авторством: Z. Biolek, та інші
Опубліковано: (2015-12-01) -
Advances in Emerging Photonic Memristive and Memristive‐Like Devices
за авторством: Wenxiao Wang, та інші
Опубліковано: (2022-10-01) -
Fault Diagnosis of the Rotating Rectifier Diode Over a TSSM Based on the Armature Current Calculation and Similarity Measurement
за авторством: Peirong Zhu, та інші
Опубліковано: (2022-01-01) -
Memristive crossbar-based circuit design of back-propagation neural network with synchronous memristance adjustment
за авторством: Le Yang, та інші
Опубліковано: (2024-04-01) -
Fault Tolerant Design, Error Detection and Correction /
за авторством: Hatcher, Stephaine, author 639643, та інші
Опубліковано: (2012)