近期，本课题组张敏老师和朱家豪同学分别以通讯作者和第一作者在材料领域国际知名期刊Advanced Functional Materials（SCI一区，2022年IF=19.924）上发表了题为“Flexible Low-Voltage MXene Floating-Gate Synaptic Transistor for Neuromorphic Computing and Cognitive Learning”的研究成果。
受生物神经网络功能的启发，神经形态计算已成为人工智能应用的一种很有前途的范式，尤其是在柔性电子领域。在各种人工突触器件中，浮栅突触晶体管表现出长期的突触可塑性，但它们面临着实现柔性兼容性的挑战。在这项工作中，首次演示了柔性MXene浮栅突触晶体管，该晶体管使用多层MXene作为浮栅，MXene纳米片作为电荷状态调制器。该设备表现出优异的机械灵活性，可以在低电压下工作，这提高了其对可穿戴电子设备的适用性。它还可以在外部压力下模仿巴甫洛夫条件反射，这表明它具有认知学习的潜力。此外，该设备通过模拟全连接神经网络用于手写数字识别，实现了92.0%的高识别准确率。这证明了它在神经形态计算中的实用性。此外，本研究还实现了MXene的图案化及其在柔性浮栅晶体管中的应用。它为柔性人工突触器件的集成制造提供了一种新的解决方案。
Neuromorphic computing, inspired by the functionality of biological neural networks, has emerged as a promising paradigm for artificial intelligence applications, especially in the field of flexible electronics. Among the various artificial synaptic devices, floating-gate synaptic transistors exhibit long-term synaptic plasticity, but they face the challenge of achieving flexible compatibility. In this work, the first demonstration of a flexible MXene floating-gate synaptic transistor is reported, which uses multiple layers of MXene as floating gates and MXene nanosheets as charge state modulators. The device shows excellent mechanical flexibility and can operate at low voltages, which improves its suitability for wearable electronic devices. It can also emulate Pavlovian conditioned reflexes under external stress, suggesting its potential for cognitive learning. Moreover, the device is utilized for handwritten digit recognition by simulating a fully connected neural network, achieving a high recognition accuracy of 92.0%. This demonstrates its practical applicability in neuromorphic computing. Besides, this research achieves the patterning of MXene and its application in flexible floating-gate transistors. It provides a new solution for the integrated fabrication of flexible artificial synaptic devices.
文章链接：
生物神经元和突触结构示意图
巴甫洛夫的狗实验示意图
用于手写数字识别的FCNN的示意图