A Diffractive Neural Network with Weight-Noise-Injection Training

TL;DR

This paper introduces a diffractive neural network trained with weight noise injection to enhance robustness against external interference, achieving accurate optical classification despite surface shape errors and noise.

Contribution

It is the first to apply weight noise injection during training to improve the noise resistance of diffractive neural networks.

Findings

The proposed SRNN maintains higher accuracy under severe noise conditions.

Weight noise injection improves the network's insensitivity to external interference.

The method achieves accurate optical classification with surface shape errors.

Abstract

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.