切片
计算机科学
人工神经网络
量化(信号处理)
聚合
光学(聚焦)
高保真
制作
深度学习
可微函数
深层神经网络
忠诚
人工智能
材料科学
算法
体素
电子工程
能量(信号处理)
相(物质)
最优化问题
能量最小化
计算机工程
光电子学
图像扭曲
卷积神经网络
计算机硬件
作者
Jiale Yao,Jiabin Bi,Yuhang Xue,Liqun Xu,Zhaohui Ye,Haowen Liu,Bowen Chen,Jincheng Ni,Jiawen Li,Dong Qing Wu,Yanlei Hu
出处
期刊:Nano Letters
[American Chemical Society]
日期:2026-08-28
卷期号:26 (36): 11979-11987
标识
DOI:10.1021/acs.nanolett.6c01607
摘要
Diffractive deep neural networks (D2NNs) provide a promising pathway toward high-speed, energy-efficient optical computing. However, a substantial discrepancy between simulation and experiment remains when devices are fabricated by two-photon polymerization (TPP) for visible/near-infrared operation. This discrepancy is primarily due to fabrication constraints. In particular, the finite voxel size of the writing focus and the layer-by-layer slicing quantization attenuate high-spatial-frequency phase features and distort the designed wavefront. Here, a fabrication-aware training (FAT) strategy is introduced to incorporate these dominant constraints into the optimization loop through a differentiable model, thereby improving the experimental performance of two-photon polymerized D2NNs. In a handwritten digit recognition task, FAT increases the average experimental energy concentration ratio (ECR) from 6.15% to 11.50%. This reduces the simulation-to-experiment discrepancy by 79.03% while preserving the classification accuracy. These results demonstrate that fabrication-aware optimization substantially improves the functional fidelity of micro/nanoscale diffractive optical computing devices.
科研通智能强力驱动
Strongly Powered by AbleSci AI