Review of diffractive deep neural networks
Yichen Sun, Mingli Dong, Mingxin Yu, Xiaolin Liu, Lianqing Zhu
Abstract
In 2018, a UCLA research group published an important paper on optical neural network (ONN) research in the journal Science . It developed the world’s first all-optical diffraction deep neural network (DNN) system, which can perform MNIST dataset classification tasks at near-light-speed. To be specific, the UCLA research group adopted a terahertz light source as the input, established the all-optical diffractive DNN (D 2 NN) model using the Rayleigh-Sommerfeld diffraction theory, optimized the model parameters using the stochastic gradient descent algorithm, and then used 3D printing technology to make the diffraction grating and built the D 2 NN system. This research opened a new ONN research direction. Here, we first review and analyze the development history and basic theory of artificial neural networks (ANNs) and ONNs. Second, we elaborate D 2 NN as holographic optical elements (HOEs) interconnected by free space light and describe the theory of D 2 NN. Then we cover the nonlinear research and application scenarios for D 2 NN. Finally, the future directions and challenges of D 2 NN are briefly discussed. Hopefully, our work can provide support and help to researchers who study the theory and application of D 2 NN in the future.