arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.05233physics.opticscs.ET
收藏

基于高非线性光纤的极限学习机的原理与度量指标

Principles and Metrics of Extreme Learning Machines Using a Highly Nonlinear Fiber

Tampere University(坦佩雷大学)

Mathilde Hary, Daniel Brunner, Lev Leybov, Piotr Ryczkowski, John M. Dudley, Goëry Genty

AI总结:

本研究基于极限学习机概念,以高非线性光纤为光计算平台,通过任务无关与任务相关实验表征系统度量指标,验证了其在MNIST图像分类上的性能优于线性系统,并揭示了功率、维度与准确率的关联规律。

摘要:

光计算利用光的固有特性,具备实现超高速、低延迟计算的潜力。本文基于极限学习机(Extreme Learning Machines)的概念,探索将高非线性光纤(highly nonlinear optical fibers, HNLFs)作为光计算平台的应用。本研究首次将与任务无关的评估引入该领域,聚焦于有效维度和一致性这两项核心度量指标,并通过实验表征了不同非线性与色散条件下的指标表现。研究表明,输入功率和光纤特性会显著影响计算系统的维度:在30 mW的输入功率下,更长的光纤和更高的色散可产生多达100个主成分(principal components, PCs),其中主成分对应系统的线性独立维度。主成分特征向量的光谱分布显示,通过维度扩展支撑计算的高维动力学特性位于1560 nm泵浦波长周围40 nm范围内,这为利用非线性薛定谔方程系统开展计算提供了通用见解。与任务相关的实验结果验证了高非线性光纤在MNIST数据集图像分类中的有效性。我们通过主成分分析实现输入数据压缩,将不同输入维度的MNIST图像注入系统,研究了输入功率对分类准确率的影响。在优化后的功率水平下,我们实现了88%的分类测试准确率,显著超过线性系统83.7%的基线水平。值得注意的是,最佳性能并非出现在最大输入功率(即最大系统维度)下,而是出现在比最大功率低一个数量级以上的功率水平。这一规律在MNIST图像压缩方面同样得到验证:当图像被强压缩至少于50个主成分时,分类准确率会大幅提升。

英文摘要:

Optical computing offers potential for ultra high-speed and low latency computation by leveraging the intrinsic properties of light. Here, we explore the use of highly nonlinear optical fibers (HNLFs) as platforms for optical computing based on the concept of Extreme Learning Machines. Task-independent evaluations are introduced to the field for the first time and focus on the fundamental metrics of effective dimensionality and consistency, which we experimentally characterize for different nonlinear and dispersive conditions. We show that input power and fiber characteristics significantly influence the dimensionality of the computational system, with longer fibers and higher dispersion producing up to 100 principal components (PCs) at input power levels of 30 mW, where the PC correspond to the linearly independent dimensions of the system. The spectral distribution of the PC's eigenvectors reveals that the high-dimensional dynamics facilitating computing through dimensionality expansion are located within 40~nm of the pump wavelength at 1560~nm, providing general insight for computing with nonlinear Schrödinger equation systems. Task-dependent results demonstrate the effectiveness of HNLFs in classifying MNIST dataset images. Using input data compression through PC analysis, we inject MNIST images of various input dimensionality into the system and study the impact of input power upon classification accuracy. At optimized power levels we achieve a classification test accuracy of 88\%, significantly surpassing the baseline of 83.7\% from linear systems. Noteworthy, we find that best performance is not obtained at maximal input power, i.e. maximal system dimensionality, but at more than one order of magnitude lower. The same is confirmed regarding the MNIST image's compression, where accuracy is substantially improved when strongly compressing the image to less than 50 PCs.

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。

↑