Denoising in Mode Conversion by Utilizing Diffractive Deep Neural Networks Optimized with Reinforcement Learning.
Optical Fiber Communications Conference and Exhibition(2024)
摘要
We propose a reinforcement-learning-optimized nonlinear physical diffractive neural network, which can simultaneously perform OAM-mode and LP-mode conversion with Gaussian noise removal. The PSNR and SSIM of the converted modes reach 27.94 dB and 0.838, respectively.
更多查看译文
关键词
Neural Network,Denoising,Mode Conversion,Gaussian Noise,Peak Signal-to-noise Ratio,Physical Network,Nonlinear Network,Nonlinear Neural Networks,Loss Function,Nonlinear Function,Optical Fiber,Image Classification,Input Modalities,Machine Learning Framework,Orbital Angular Momentum,Output Mode,Deep Q-learning,Phase Plate
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要