Kim Guhyun, Kornijcuk Vladimir, Kim Dohun, Kim Inho, Hwang Cheol Seong, Jeong Doo Seok
Center for Electronic Materials, Korea Institute of Science and Technology, Hwarangno 14-gil 5, Seongbuk-gu, Seoul 02792, Korea.
The Department of Materials Science and Engineering and Inter-University Semiconductor Research Center, Seoul National University, Gwanakro 1, Gwanak-gu, Seoul 08826, Korea.
Micromachines (Basel). 2019 Mar 27;10(4):219. doi: 10.3390/mi10040219.
An artificial neural network was utilized in the behavior inference of a random crossbar array (10 × 9 or 28 × 27 in size) of nonvolatile binary resistance-switches (in a high resistance state (HRS) or low resistance state (LRS)) in response to a randomly applied voltage array. The employed artificial neural network was a multilayer perceptron (MLP) with leaky rectified linear units. This MLP was trained with 500,000 or 1,000,000 examples. For each example, an input vector consisted of the distribution of resistance states (HRS or LRS) over a crossbar array plus an applied voltage array. That is, for a × array where voltages are applied to its rows, the input vector was × ( + 1) long. The calculated (correct) current array for each random crossbar array was used as data labels for supervised learning. This attempt was successful such that the correlation coefficient between inferred and correct currents reached 0.9995 for the larger crossbar array. This result highlights MLP that leverages its versatility to capture the quantitative linkage between input and output across the highly nonlinear crossbar array.
利用人工神经网络对非易失性二元电阻开关（处于高电阻状态（HRS）或低电阻状态（LRS））的随机交叉阵列（尺寸为10×9或28×27）在随机施加电压阵列时的行为进行推断。所采用的人工神经网络是一个带有泄漏整流线性单元的多层感知器（MLP）。该MLP用500,000或1,000,000个示例进行训练。对于每个示例，输入向量由交叉阵列上电阻状态（HRS或LRS）的分布加上施加的电压阵列组成。也就是说，对于一个向其m行施加电压的m×n阵列，输入向量长度为m×(n + 1)。为每个随机交叉阵列计算的（正确的）电流阵列用作监督学习的数据标签。这种尝试是成功的，对于较大的交叉阵列，推断电流与正确电流之间的相关系数达到了0.9995。这一结果突出了MLP利用其通用性来捕捉高度非线性交叉阵列中输入和输出之间定量联系的能力。
