加权噪声注入训练的衍射神经网络
A Diffractive Neural Network with Weight-Noise-Injection Training
摘要：
我们提出了一种基于加权噪声注入训练的具有较强鲁棒性的衍射神经网络，在衍射层具有一定表面形状误差的情况下，实现了基于光学的准确快速分类。据我们所知，这是第一次在训练过程中使用注入权重噪声来减少外部干扰对深度学习推理结果的影响。在所提出的方法中，衍射神经网络在权重噪声注入模式下学习输入图像和标签之间的映射，使网络的权重对适度的变化不敏感，从而以较低的成本提高了网络的抗噪性。通过比较网络在不同噪声下的精度，验证了所提出的网络（SRNN）在严重噪声下仍然保持较高的精度。
英文摘要：
We propose a diffractive neural network with strong robustness based on Weight Noise Injection training, which achieves accurate and fast optical-based classification while diffraction layers have a certain amount of surface shape error. To the best of our knowledge, it is the first time that using injection weight noise during training to reduce the impact of external interference on deep learning inference results. In the proposed method, the diffractive neural network learns the mapping between the input image and the label in Weight Noise Injection mode, making the network's weight insensitive to modest changes, which improve the network's noise resistance at a lower cost. By comparing the accuracy of the network under different noise, it is verified that the proposed network (SRNN) still maintains a higher accuracy under serious noise.
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。
