Ultrasensitive 2D Vermiculite Inorganic Liquid Crystals for Nonlinear Optical Activation

Optical neural networks (ONNs) have emerged as promising architectures for vision tasks due to their inherent parallelism and potential low energy consumption. Currently, achieving reconfigurable nonlinear optical activation with high responsiveness remains challenging in ONNs. In this study, we propose a reconfigurable configuration utilizing two-dimensional (2D) material-based inorganic liquid crystal (LC) as an optical-to-optical nonlinear activator. The ultrasensitive electro-optical effect of 2D vermiculite (VMT) enables the proposed configuration, where the nonlinear activation is sensitively modulated by a small operational electric field in a range of <0.4 V mm^-1, orders of magnitude lower than other LCs. We validate the capability and feasibility of the 2D VMT inorganic LC-based nonlinear optical activator for ONNs through emulation on benchmark data sets for image recognition with accuracy of 99.69, 92.56, and 79.19% for MNIST, Fashion-MNIST, and CIFAR-10, respectively. This work shows the potential of 2D material inorganic LCs as activators in ONNs, offering promising avenues for future advanced computational applications.