光子随机涌现存储:利用散射内禀模式实现可编程深度分类
Photonic Stochastic Emergent Storage: Exploiting Scattering-intrinsic Patterns for Programmable Deep Classification
AI总结:
提出随机涌现存储(SES)方法,利用白漆浑浊介质中的光散射随机传输矩阵作为原型,在类Hopfield网络中实现任意模式存储与光速分类,无需额外制造即可同时存储数千记忆并支持深度光学分类。
摘要:
无序是自然系统的普遍特征,提供了大量非重复模式。在本研究中,我们提出了一种新颖的存储方法,利用自然产生的随机结构在存储设备中存储任意模式。该方法即随机涌现存储(SES),建立在涌现原型的概念之上,其中使用不完美示例(原型)的训练集,通过涌现过程在类Hopfield网络中实例化一个原型。我们在光子领域展示了这一非Hebbian范式,利用随机传输矩阵(控制白漆浑浊介质中光散射)作为原型。通过实现可编程硬件,我们成功实现并实验验证了存储任意原型并以光速执行分类的能力。利用介观扩散激发的大量模式,我们的方法能够同时存储数千个记忆,而无需任何额外的制造工作。类似于内容可寻址存储器,所有存储的记忆可以集体与给定模式进行比较,以识别匹配元素。此外,通过将记忆在空间上组织为不同类别,它们成为更高级分类(深层)光学分类层中的特征。
英文摘要:
Disorder is a pervasive characteristic of natural systems, offering a wealth of non-repeating patterns. In this study, we present a novel storage method that harnesses naturally-occurring random structures to store an arbitrary pattern in a memory device. This method, the stochastic emergent storage (SES), builds upon the concept of emergent archetypes, where a training set of imperfect examples (prototypes) is employed to instantiate an archetype in an Hopfield-like network through emergent processes. We demostrate this non-Hebbian paradigm in the photonic domain by utilizing random transmission matrices, which govern light scattering in a white-paint turbid medium, as prototypes. Through the implementation of programmable hardware, we successfully realize and experimentally validate the capability to store an arbitrary archetype and perform classification at the speed of light. Leveraging the vast number of modes excited by mesoscopic diffusion, our approach enables the simultaneous storage of thousands of memories without requiring any additional fabrication efforts. Similar to a content addressable memory, all stored memories can be collectively assessed against a given pattern to identify the matching element. Furthermore, by organizing memories spatially into distinct classes, they become features within a higher-level categorical (deeper) optical classification layer.
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。