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 (${{\rm{D}}^2}{\rm{NN}}$) 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 ${{\rm{D}}^2}{\rm{NN}}$ 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 ${{\rm{D}}^2}{\rm{NN}}$ as holographic optical elements (HOEs) interconnected by free space light and describe the theory of ${{\rm{D}}^2}{\rm{NN}}$. Then we cover the nonlinear research and application scenarios for ${{\rm{D}}^2}{\rm{NN}}$. Finally, the future directions and challenges of ${{\rm{D}}^2}{\rm{NN}}$ are briefly discussed. Hopefully, our work can provide support and help to researchers who study the theory and application of ${{\rm{D}}^2}{\rm{NN}}$ in the future.
© 2023 Optica Publishing Group
Full Article | PDF ArticleMore Like This
Mingzhu Song, Runze Li, and Junsheng Wang
Appl. Opt. 62(4) 1082-1087 (2023)
Takumi Fujita, Hotaka Sakaguchi, Jian Zhang, Hirofumi Nonaka, Satoshi Sumi, Hiroyuki Awano, and Takayuki Ishibashi
Opt. Express 30(20) 36889-36899 (2022)
Caihong Teng, Weijie He, Wen Du, Jiang Wu, and Zhiming Wang
J. Opt. Soc. Am. B 40(8) 2007-2012 (2023)