The development of high-performance neuromorphic phototransistors is of paramount importance for image perception and depth memory learning. Here, based on metal-oxide heterojunction architecture, artificial synaptic phototransistors with synaptic plasticity have been achieved, demonstrating an artificial synapse that integrates central and optic nerve functions. Thanks to the sensitive light-detection properties, the optical power consumption of such photonic artificial synapses can be as low as 22 pico-joules, which is extremely competitive compared with other pure metal oxide photoelectric synapses ever reported. What is more, owing to its good short-term (STP) and tunable amplitude-frequency characteristics, the as-constructed device can function as a biomimetic high-pass filter for picture edge detection. Dual-mode synaptic modulation has been performed, combining photonic pulse with gate voltage stimulus. After photoelectric-synergistic modulation, the high synaptic weights enable the device to simulate complex neural learning rules for neuromorphic applications, including gesture recognition, image perception in the visual system, and classically conditioned reflexes. These results suggest that the current oxide-based heterojunction architecture displays potential application in future multifunction neuromorphic devices and systems.

中文翻译：

---

具有异质结架构的高性能 IGZO/In2O3 NW/IGZO 光电晶体管，用于图像处理和神经形态计算

高性能神经形态光电晶体管的开发对于图像感知和深度记忆学习至关重要。这里，基于金属氧化物异质结结构，实现了具有突触可塑性的人工突触光电晶体管，展示了集成中枢和视神经功能的人工突触。得益于灵敏的光检测特性，这种光子人工突触的光功耗可低至22皮焦耳，与迄今为止报道的其他纯金属氧化物光电突触相比极具竞争力。此外，由于其良好的短期（STP）和可调幅频特性，所构建的器件可以用作图像边缘检测的仿生高通滤波器。已经执行了双模式突触调制，将光子脉冲与栅极电压刺激相结合。经过光电协同调制后，高突触权重使该设备能够模拟神经形态应用的复杂神经学习规则，包括手势识别、视觉系统中的图像感知和经典条件反射。这些结果表明，当前基于氧化物的异质结架构在未来的多功能神经形态设备和系统中显示出潜在的应用。