Hsin Tzu-Chuan, Lin Chun-Yi, Wang Po-Chuan, Yang Chun, Pai Chi-Feng
Department of Materials Science and Engineering, National Taiwan University, Taipei, 10617, Taiwan.
Adv Sci (Weinh). 2025 Jun;12(22):e2417735. doi: 10.1002/advs.202417735. Epub 2025 Apr 26.
The development of energy-efficient, brain-inspired neuromorphic computing demands advanced memory devices capable of mimicking synaptic behavior to achieve high accuracy and adaptability. In this study, three types of all-electrically controlled, field-free spin synapse devices designed with unique spintronic structures presented: the Néel orange-peel effect, interlayer Dzyaloshinskii-Moriya interaction (i-DMI), and tilted anisotropy. To systematically evaluate their neuromorphic potential, a benchmarking framework is introduced that characterizes cycle-to-cycle (CTC) variation, a critical factor for reliable synaptic weight updates. Among these designs, the tilted anisotropy device achieves an 11-state memory with minimal CTC variation (2%), making it particularly suited for complex synaptic emulation. Through comprehensive benchmarking, this multi-state device in convolutional neural networks (CNNs) using post-training quantization is implemented. Results indicate that per-channel quantization, particularly with the min-max and mean squared error (MSE) observers, enhances classification accuracy on the CIFAR-10 dataset, achieving up to 81.51% and 81.12% in ResNet-18-values that closely approach the baseline accuracy. This evaluation underscores the potential of field-free spintronic synapses in neuromorphic architectures, offering an area-efficient solution that integrates multi-state functionality with robust switching performance. The findings highlight the promise of these devices in advancing neuromorphic computing, contributing to energy-efficient, high-performance systems inspired by neural processes.
节能型、受大脑启发的神经形态计算的发展需要先进的存储设备，这些设备能够模仿突触行为以实现高精度和适应性。在本研究中，展示了三种采用独特自旋电子结构设计的全电控、无磁场自旋突触器件：奈尔橙皮效应、层间Dzyaloshinskii-Moriya相互作用（i-DMI）和倾斜各向异性。为了系统地评估它们的神经形态潜力，引入了一个基准框架，该框架表征了逐周期（CTC）变化，这是可靠突触权重更新的关键因素。在这些设计中，倾斜各向异性器件实现了具有最小CTC变化（2%）的11态存储器，使其特别适合复杂的突触模拟。通过全面的基准测试，在使用训练后量化的卷积神经网络（CNN）中实现了这种多态器件。结果表明，每通道量化，特别是使用最小-最大和均方误差（MSE）观测器时，提高了CIFAR-10数据集上的分类准确率，在ResNet-18中达到了高达81.51%和81.12%的值，这些值与基线准确率非常接近。该评估强调了无磁场自旋电子突触在神经形态架构中的潜力，提供了一种面积高效的解决方案，将多态功能与强大的开关性能集成在一起。研究结果突出了这些器件在推进神经形态计算方面的前景，有助于实现受神经过程启发的节能、高性能系统。
