Pham Khoa Van, Tran Son Bao, Nguyen Tien Van, Min Kyeong-Sik
Electrical Engineering Department, Kookmin University, Seoul 02707, Korea.
Micromachines (Basel). 2019 Feb 20;10(2):141. doi: 10.3390/mi10020141.
For realizing neural networks with binary memristor crossbars, memristors should be programmed by high-resistance state (HRS) and low-resistance state (LRS), according to the training algorithms like backpropagation. Unfortunately, it takes a very long time and consumes a large amount of power in training the memristor crossbar, because the program-verify scheme of memristor-programming is based on the incremental programming pulses, where many programming and verifying pulses are repeated until the target conductance. Thus, this reduces the programming time and power is very essential for energy-efficient and fast training of memristor networks. In this paper, we compared four different programming schemes, which are F-F, C-F, F-C, and C-C, respectively. C-C means both HRS and LRS are coarse-programmed. C-F has the coarse-programmed HRS and fine LRS, respectively. F-C is vice versa of C-F. In F-F, both HRS and LRS are fine-programmed. Comparing the error-energy products among the four schemes, C-F shows the minimum error with the minimum energy consumption. The asymmetrical coarse HRS and fine LRS can reduce the time and energy during the crossbar training significantly, because only LRS is fine-programmed. Moreover, the asymmetrical C-F can maintain the network's error as small as F-F, which is due to the coarse-programmed HRS that slightly degrades the error.
为了用二元忆阻器交叉阵列实现神经网络，忆阻器应根据诸如反向传播等训练算法，通过高电阻状态（HRS）和低电阻状态（LRS）进行编程。不幸的是，训练忆阻器交叉阵列需要很长时间且消耗大量能量，因为忆阻器编程的编程-验证方案基于增量编程脉冲，其中许多编程和验证脉冲会重复进行，直到达到目标电导。因此，减少编程时间和功耗对于忆阻器网络的节能和快速训练至关重要。在本文中，我们比较了四种不同的编程方案，分别是F-F、C-F、F-C和C-C。C-C表示高电阻状态（HRS）和低电阻状态（LRS）均采用粗编程。C-F分别对高电阻状态（HRS）采用粗编程，对低电阻状态（LRS）采用精细编程。F-C与C-F相反。在F-F中，高电阻状态（HRS）和低电阻状态（LRS）均采用精细编程。比较这四种方案的误差-能量积，C-F显示出最小的误差和最小的能量消耗。非对称的粗高电阻状态（HRS）和精细低电阻状态（LRS）可以显著减少交叉阵列训练期间的时间和能量，因为只有低电阻状态（LRS）采用精细编程。此外，非对称的C-F可以将网络误差保持得与F-F一样小，这是由于粗编程的高电阻状态（HRS）会使误差略有下降。
