Hwang Sungmin, Yu Junsu, Song Min Suk, Hwang Hwiho, Kim Hyungjin
Department of AI Semiconductor Engineering, Korea University, Sejong, 30019, South Korea.
Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, South Korea.
Adv Sci (Weinh). 2023 Nov;10(32):e2303817. doi: 10.1002/advs.202303817. Epub 2023 Sep 26.
The progress of artificial intelligence and the development of large-scale neural networks have significantly increased computational costs and energy consumption. To address these challenges, researchers are exploring low-power neural network implementation approaches and neuromorphic computing systems are being highlighted as potential candidates. Specifically, the development of high-density and reliable synaptic devices, which are the key elements of neuromorphic systems, is of particular interest. In this study, an 8 × 16 memcapacitor crossbar array that combines the technological maturity of flash cells with the advantages of NAND flash array structure is presented. The analog properties of the array with high reliability are experimentally demonstrated, and vector-matrix multiplication with extremely low error is successfully performed. Additionally, with the capability of weight fine-tuning characteristics, a spiking neural network for CIFAR-10 classification via off-chip learning at the wafer level is implemented. These experimental results demonstrate a high level of accuracy of 92.11%, with less than a 1.13% difference compared to software-based neural networks (93.24%).
人工智能的进步和大规模神经网络的发展显著增加了计算成本和能源消耗。为应对这些挑战，研究人员正在探索低功耗神经网络实现方法，神经形态计算系统作为潜在候选方案受到关注。具体而言，作为神经形态系统关键元件的高密度且可靠的突触器件的开发尤为令人感兴趣。在本研究中，提出了一种8×16忆阻器交叉阵列，其结合了闪存单元的技术成熟度与NAND闪存阵列结构的优势。通过实验证明了该阵列具有高可靠性的模拟特性，并成功执行了误差极低的向量-矩阵乘法。此外，凭借权重微调特性，实现了一种用于通过晶圆级片外学习对CIFAR-10进行分类的脉冲神经网络。这些实验结果表明准确率高达92.11%，与基于软件的神经网络（93.24%）相比差异小于1.13%。
