Dot-product computation and logistic regression with 2D hexagonal-boron nitride (h-BN) memristor arrays
Dot-product computation and logistic regression with 2D hexagonal-boron nitride (h-BN) memristor arrays
复制标题
DOI：
10.1088/2053-1583/acdfe1
复制
发表时间：
2023-06
期刊：
影响因子：
5.5
通讯作者：
Sahra Afshari;S. Radhakrishnan;Jing Xie;Mirembe Musisi-Nkambwe;Jian Meng;Wangxin He;J.-s. Seo
中科院分区：
文献类型：
--
作者：
Sahra Afshari;S. Radhakrishnan;Jing Xie;Mirembe Musisi-Nkambwe;Jian Meng;Wangxin He;J.-s. Seo
本工作报告的硬件实现上的二维（2D）六方氮化硼（h-BN）忆阻器阵列的模拟点积运算。这超出了以前的工作，研究隔离器件的特性，对模拟神经网络加速器的应用程序的基础上的2D忆阻器阵列。忆阻器阵列的晶片级制造通过CVD生长的少层（8层）h-BN膜的大面积转移来实现。单个器件实现了>10的开/关比、低电压工作（≤ 0.5 V置位/V复位）、良好的耐久性（>6000个编程步骤）和良好的保持力（>104 s）。点积操作显示出出色的线性度和可重复性，读取能耗低（每次操作200 aJ至20 fJ），在各种测量周期内误差和偏差最小。此外，我们提出了一个随机逻辑回归算法在二维h-BN忆阻器硬件的噪声图像的分类的实施。有前途的电阻开关特性，点积计算的性能，以及h-BN忆阻器中逻辑回归的成功演示，标志着下一代神经形态计算系统集成2D材料的重要一步。
This work reports on the hardware implementation of analog dot-product operation on arrays of two-dimensional (2D) hexagonal boron nitride (h-BN) memristors. This extends beyond previous work that studied isolated device characteristics towards the application of analog neural network accelerators based on 2D memristor arrays. The wafer-level fabrication of the memristor arrays is enabled by large-area transfer of CVD-grown few-layer (8 layers) h-BN films. Individual devices achieve an on/off ratio of >10, low voltage operation (∼0.5 V set/V reset), good endurance (>6000 programming steps), and good retention (>104 s). The dot-product operation shows excellent linearity and repeatability, with low read energy consumption (∼200 aJ to 20 fJ per operation), with minimal error and deviation over various measurement cycles. Moreover, we present the implementation of a stochastic logistic regression algorithm in 2D h-BN memristor hardware for the classification of noisy images. The promising resistive switching characteristics, performance of dot-product computation, and successful demonstration of logistic regression in h-BN memristors signify an important step towards the integration of 2D materials for next-generation neuromorphic computing systems.