Xu Zefeng, Tang Baoshan, Zhang Xiangyu, Leong Jin Feng, Pan Jieming, Hooda Sonu, Zamburg Evgeny, Thean Aaron Voon-Yew
Integrative Sciences and Engineering Programme, NUS Graduate School, National University of Singapore, Singapore, Singapore.
Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore, 117583, Singapore.
Light Sci Appl. 2022 Oct 6;11(1):288. doi: 10.1038/s41377-022-00976-5.
Photonic neural network has been sought as an alternative solution to surpass the efficiency and speed bottlenecks of electronic neural network. Despite that the integrated Mach-Zehnder Interferometer (MZI) mesh can perform vector-matrix multiplication in photonic neural network, a programmable in-situ nonlinear activation function has not been proposed to date, suppressing further advancement of photonic neural network. Here, we demonstrate an efficient in-situ nonlinear accelerator comprising a unique solution-processed two-dimensional (2D) MoS Opto-Resistive RAM Switch (ORS), which exhibits tunable nonlinear resistance switching that allow us to introduce nonlinearity to the photonic neuron which overcomes the linear voltage-power relationship of typical photonic components. Our reconfigurable scheme enables implementation of a wide variety of nonlinear responses. Furthermore, we confirm its feasibility and capability for MNIST handwritten digit recognition, achieving a high accuracy of 91.6%. Our accelerator constitutes a major step towards the realization of in-situ photonic neural network and pave the way for the integration of photonic integrated circuits (PIC).
光子神经网络已被视作一种替代方案，以突破电子神经网络在效率和速度方面的瓶颈。尽管集成马赫曾德尔干涉仪（MZI）网格能够在光子神经网络中执行向量矩阵乘法，但迄今为止尚未提出可编程的原位非线性激活函数，这抑制了光子神经网络的进一步发展。在此，我们展示了一种高效的原位非线性加速器，它由独特的溶液处理二维（2D）MoS光阻变随机存取存储器开关（ORS）组成，该开关呈现出可调谐的非线性电阻切换特性，使我们能够将非线性引入光子神经元，从而克服典型光子组件的线性电压 - 功率关系。我们的可重构方案能够实现多种非线性响应。此外，我们证实了其在MNIST手写数字识别中的可行性和能力，实现了91.6%的高精度。我们的加速器朝着实现原位光子神经网络迈出了重要一步，为光子集成电路（PIC）的集成铺平了道路。
