As a representative next-generation device/circuit technology beyond CMOS, diffractive optical neural networks (DONNs) have shown promising advantages over conventional deep neural networks due to extreme fast computation speed (light speed) and low energy consumption. However, there is a mismatch, i.e., significant prediction accuracy loss, between the DONN numerical modelling and physical optical device deployment, because of the interpixel interaction within the diffractive layers. In this work, we propose a physics-aware diffractive optical neural network training framework to reduce the performance difference between numerical modeling and practical deployment. Specifically, we propose the roughness modeling regularization in the training process and integrate the physics-aware sparsification method to introduce sparsity to the phase masks to reduce sharp phase changes between adjacent pixels in diffractive layers. We further develop $2\pi$ periodic optimization to reduce the roughness of the phase masks to preserve the performance of DONN. Experiment results demonstrate that, compared to state-of-the-arts, our physics-aware optimization can provide $35.7\%$, $34.2\%$, $28.1\%$, and $27.3\%$ reduction in roughness with only accuracy loss on MNIST, FMNIST, KMNIST, and EMNIST, respectively.
翻译:作为一种超越CMOS的代表性下一代器件/电路技术,衍射性光学神经网络(DONN)由于计算速度极快(光速)和能耗低而在传统的深度神经网络中显示出极具有潜力的优势。然而,由于衍射层中的像素间相互作用,在DONN的数值建模和光学器件实际部署之间存在不匹配,即存在显著的预测精度损失。在这项工作中,我们提出了一种物理感知型衍射性光学神经网络训练框架,以减少数值建模和实际部署之间的性能差异。具体而言,在训练过程中我们提出了粗糙度建模正则化,并集成了物理感知的稀疏化方法,以向衍射层的像素间引入稀疏性,以减少锐利的相位变化。我们进一步开发了2π周期优化来降低相位掩模的粗糙度,以保持DONN的性能。实验结果表明,相对于最先进技术,我们的物理感知型优化可以提供对MNIST、FMNIST、KMNIST和EMNIST的粗糙度分别降低35.7%、34.2%、28.1%和27.3%的改进效果,仅有轻微的精度损失。