Jetty Prabana, Mohanan Kannan Udaya, Jammalamadaka S Narayana
Magnetic Materials and Device Physics Laboratory, Department of Physics, Indian Institute of Technology Hyderabad, Hyderabad, 502 284, India.
Department of Electronic Engineering, Gachon University, Seongnam-si, Gyeonggi-do, 13120, Republic of Korea.
Nanotechnology. 2023 Apr 12;34(26). doi: 10.1088/1361-6528/acc811.
We report on the-FeO-based artificial synaptic resistive random access memory device, which is a promising candidate for artificial neural networks (ANN) to recognize the images. The device consists of a structure Ag/-FeO/FTO and exhibits non-volatility with analog resistive switching characteristics. We successfully demonstrated synaptic learning rules such as long-term potentiation, long-term depression, and spike time-dependent plasticity. In addition, we also presented off-chip training to obtain good accuracy by backpropagation algorithm considering the synaptic weights obtained from-FeObased artificial synaptic device. The proposed-FeO-based device was tested with the FMNIST and MNIST datasets and obtained a high pattern recognition accuracy of 88.06% and 97.6% test accuracy respectively. Such a high pattern recognition accuracy is attributed to the combination of the synaptic device performance as well as the novel weight mapping strategy used in the present work. Therefore, the ideal device characteristics and high ANN performance showed that the fabricated device can be useful for practical ANN implementation.
我们报道了基于-FeO的人工突触电阻式随机存取存储器器件，它是人工神经网络（ANN）识别图像的一个有前途的候选者。该器件由Ag/-FeO/FTO结构组成，并具有非易失性和模拟电阻切换特性。我们成功地演示了诸如长时程增强、长时程抑制和尖峰时间依赖可塑性等突触学习规则。此外，考虑到从基于-FeO的人工突触器件获得的突触权重，我们还提出了片外训练，以通过反向传播算法获得良好的准确性。所提出的基于-FeO的器件在FMNIST和MNIST数据集上进行了测试，分别获得了88.06%的高模式识别准确率和97.6%的测试准确率。如此高的模式识别准确率归因于突触器件性能以及本工作中使用的新颖权重映射策略的结合。因此，理想的器件特性和高ANN性能表明，所制造的器件可用于实际的ANN实现。
