The ultimate goal of artificial intelligence is to mimic the human brain to perform decision-making and control directly from high-dimensional sensory input. All-optical diffractive neural networks provide a promising solution for implementing artificial intelligence with high-speed and low-power consumption. To date, most of the reported diffractive neural networks focus on single or multiple tasks that do not involve interaction with the environment, such as object recognition and image classification. In contrast, the networks that can perform decision-making and control, to our knowledge, have not been developed yet. Here, we propose using deep reinforcement learning to implement diffractive neural networks that imitate human-level decision-making and control capability. Such networks allow for finding optimal control policies through interaction with the environment and can be readily realized with the dielectric metasurfaces. The superior performances of these networks are verified by engaging three types of classic games, Tic-Tac-Toe, Super Mario Bros., and Car Racing, and achieving the same or even higher levels comparable to human players. Our work represents a solid step of advancement in diffractive neural networks, which promises a fundamental shift from the target-driven control of a pre-designed state for simple recognition or classification tasks to the high-level sensory capability of artificial intelligence. It may find exciting applications in autonomous driving, intelligent robots, and intelligent manufacturing.
翻译:人工智能的最终目标是模仿人类大脑,直接从高维感官输入中进行决策和控制。全光 diffractive神经网络为采用高速和低电消耗的人工智能提供了有希望的解决方案。迄今为止,大多数报告的 diffractive神经网络侧重于单一或多重任务,但不涉及与环境的互动,例如物体识别和图像分类。相比之下,能够进行决策和控制的网络,与我们的知识相比,尚未开发出来。在这里,我们提议利用深度强化学习来实施与人类决策和控制能力相仿的硬性神经网络。这种网络通过与环境的互动,可以找到最佳的控制政策,并且可以很容易地与电磁元表面实现。这些网络的优异性表现是通过三种类型的经典游戏(Tic-Tac-Toe, Super Mario Bros.)和Car Racing,以及达到与人类参与者相同的甚至更高的智能水平。我们的工作代表了在硬性神经神经网络进步的一个坚实的一步,即模仿性神经神经网络的升级和智能网络,可以将一个基本的感官动力化的智能应用水平定位,从而将它定位到一个基本的智能化的机器人控制水平。