All‐Dielectric Metasurface Empowered Optical‐Electronic Hybrid Neural Networks. Issue 10 (20th July 2022)

• Record Type: Journal Article
• Authors: Qu, Geyang; Cai, Guiyi; Sha, Xinbo; Chen, Qinmiao; Cheng, Jiaping; Zhang, Yao; Han, Jiecai; Song, Qinghai; Xiao, Shumin
• Is Part Of: Laser & photonics reviews. Volume 16:Issue 10(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-07-20
• Subjects: diffraction deep neural networks -- edge devices -- metasurfaces; Lasers -- Periodicals; Photonics -- Periodicals; Lasers -- Périodiques; Photonique -- Périodiques; 621.36
• DOI: 10.1002/lpor.202100732
• Languages: English
• ISSNs: 1863-8880

Abstract

Abstract: Optical computing has a series of advantages over its electronic counterpart, e.g., low energy consumption, high speed, and intrinsic parallelism. Diffraction deep neural networks (D 2 NNs) are a prominent example capable of processing images directly without addressing the spatial locations of each element. Despite the great successes, the D 2 NNs typically utilize the multilayer framework and face the severe challenge of misalignment in the optical region. Herein, a single metasurface‐based optical‐electronic hybrid neural network (OENN) is proposed and experimentally demonstrated. The OENN is composed of a titanium dioxide (TiO2 ) metasurface and a fully‐connected electronic layer. The combination of nonlocal neural layer and nonlinear transformation has significantly expanded the neural network capacity. Consequently, the classification accuracy on handwritten digits recognition can still be as high as 98.05% without employing the architecture of cascaded metasurfaces. The OENN shall shed light on the practical applications of optical computing in the visible spectrum. Abstract : A metasurface‐empowered optical‐electronic hybrid neural network in visible range is demonstrated, achieving record‐high experimental blind‐test accuracy on Modified National Institute of Standards and Technology database (MNIST). The amplitude‐intensity conversion on the camera introduces the necessary nonlinearity which expands the computing potential for complex missions. The ultracompact framework suppresses the inevitable error and misalignment that puzzling the area.