Decision-making and control with diffractive optical networks
Jumin Qiu, Shuyuan Xiao, Lujun Huang, Andrey E. Miroshnichenko, Dejian Zhang, Tingting Liu, Tianbao Yu
Nanchang University East China Normal University UNSW Sydney UNSW Canberra
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
The ultimate goal of artificial intelligence (AI) is to mimic the human brain to perform decision-making and control directly from high-dimensional sensory input. Diffractive optical networks (DONs) provide a promising solution for implementing AI with high speed and low power-consumption. Most reported DONs focus on tasks that do not involve environmental interaction, such as object recognition and image classification. By contrast, the networks capable of decision-making and control have not been developed. Here, we propose using deep reinforcement learning to implement DONs that imitate human-level decision-making and control capability. Such networks, which take advantage of a residual architecture, allow finding optimal control policies through interaction with the environment and can be readily implemented with existing optical devices. The superior performance is verified using three types of classic games: tic-tac-toe, Super Mario Bros., and Car Racing. Finally, we present an experimental demonstration of playing tic-tac-toe using the network based on a spatial light modulator. Our work represents a solid step forward in advancing DONs, which promises a fundamental shift from simple recognition or classification tasks to the high-level sensory capability of AI. It may find exciting applications in autonomous driving, intelligent robots, and intelligent manufacturing.
逐年被引趋势
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AINeural Networks and Reservoir Computing
Random lasers and scattering media · Advanced Memory and Neural Computing
参考文献 51
此处列出前 3 条
引用本文 17
按被引量排序,此处列出前 3 条