arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.01616physics.optics
收藏

流形划分诱导的时序光学推理与决策框架用于光子计算

Manifold partitioning induced sequential optical reasoning and decision framework for photonic computing

Westlake University(西湖大学);Westlake Institute for Optoelectronics(西湖光电研究院)

Zhihao Li, Jing Pan, Wei Yan, Yu Xie, Lingmei Ma, Xiaoyu Sun, Min Qiu

AI总结:

提出时序光学推理与决策(SORD)框架,通过几何引导的数据划分将全局任务分解为粗到细的步骤,使单层衍射光学神经网络实现100类光纤散斑分类,准确率94%,能效23.3 TOPS/W。

摘要:

真实世界数据本质上嵌入高度纠缠的流形中,因此提取可分离表示成为人工智能(AI)系统的核心挑战。尽管光学神经网络(ONN)提供超快和节能的数据处理,但其能力受限于有限的物理深度。在此,我们引入一种时序光学推理与决策(SORD)框架,该架构通过几何引导的数据划分将全局任务分解为从粗到细的步骤,执行时间序列化的层次推理。在每一步,SORD通过动态算子选择执行小规模推理,有效降低整体任务复杂度,而无需扩展物理架构。实验上,SORD使单层衍射ONN实现了原本难以处理的100类光纤散斑分类,准确率达94%,系统能效为23.3 TOPS/W。这种高保真识别在人机界面中进一步得到验证,实现了实时交互的全光传感。总体而言,我们的工作建立了一种可扩展且硬件高效的方法,以扩展紧凑型光子AI系统的有效表达能力,并可能推动其在需要实时传感、推理和控制的场景中的部署。

英文摘要:

Real-world data are intrinsically embedded in highly entangled manifolds, making the extraction of separable representations a central challenge for artificial intelligent (AI) systems. While optical neural networks (ONNs) offer ultrafast and energy-efficient data processing, their capacity is constrained by limited physical depth. Here, we introduce a sequential optical reasoning and decision (SORD) framework, an architecture that performs time-sequenced hierarchical inference by decomposing global tasks into coarse-to-fine steps via geometry-guided data partitioning. At each step, SORD executes small reasoning via dynamic operator selection, effectively reducing the overall task complexity without scaling up physical architecture. Experimentally, SORD enables a single-layer diffractive ONN to achieve otherwise intractable 100-class optical fiber speckle classification with 94% accuracy and a system energy efficiency of 23.3 TOPS/W. This high-fidelity recognition is further examined in a human-machine interface, featuring real-time interactive all-optical sensing. Overall, our work establishes a scalable and hardware-efficient approach to expanding the effective expressivity of compact photonic AI systems, and may advance their deployment in applications requiring real-time sensing, inference, and control.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑