arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2208.09398physics.opticscs.AIcs.ETcs.LGphysics.app-ph
收藏

用于机器学习的非线性光学数据Transformer

Nonlinear Optical Data Transformer for Machine Learning

Ecole Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院);ETH Zurich(苏黎世联邦理工学院);Versics AG(Versics股份公司)

Mustafa Yildirim, Ilker Oguz, Fabian Kaufmann, Marc Reig Escale, Rachel Grange, Demetri Psaltis, Christophe Moser

摘要:

现代机器学习模型使用越来越多的参数来训练(GPT-3的1750亿个参数)大型数据集,以获得更好的性能。越大越好已经成为常态。光学计算已经被重新唤醒,作为一种潜在的解决方案,通过光学加速器进行线性操作,同时减少电力大规模计算。然而,要实现高效的计算与光,创建和控制非线性光学,而不是电子仍然是一个挑战。本研究探讨了水库计算(RC)的方法,即14毫米长的少模波导在铌酸锂绝缘体上被用作一个复杂的非线性光学处理器。数据集在飞秒脉冲的频谱上进行数字编码,然后在波导中发射。输出频谱与输入非线性相关。我们的实验表明,一个简单的数字线性分类器与784个参数使用的输出光谱从波导作为输入增加了几个数据库的分类精度相比,非变换的数据,约10 $\%$。相比之下,需要具有40000个参数的深度数字神经网络(NN)才能达到相同的精度。将参数的数量减少因子$\sim$ 50说明紧凑的光学RC方法可以与深度数字NN同等地执行。

英文摘要:

Modern machine learning models use an ever-increasing number of parameters to train (175 billion parameters for GPT-3) with large datasets to obtain better performance. Bigger is better has been the norm. Optical computing has been reawakened as a potential solution to large-scale computing through optical accelerators that carry out linear operations while reducing electrical power. However, to achieve efficient computing with light, creating and controlling nonlinearity optically rather than electronically remains a challenge. This study explores a reservoir computing (RC) approach whereby a 14 mm long few-mode waveguide in LiNbO3 on insulator is used as a complex nonlinear optical processor. A dataset is encoded digitally on the spectrum of a femtosecond pulse which is then launched in the waveguide. The output spectrum depends nonlinearly on the input. We experimentally show that a simple digital linear classifier with 784 parameters using the output spectrum from the waveguide as input increased the classification accuracy of several databases compared to non-transformed data, approximately 10$\%$. In comparison, a deep digital neural network (NN) with 40000 parameters was necessary to achieve the same accuracy. Reducing the number of parameters by a factor of $\sim$50 illustrates that a compact optical RC approach can perform on par with a deep digital NN.

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。

↑