多波长二值光学衍射神经网络
Multi-Wavelength Binary Optical Diffraction Neural Network
DOI: 10.12677/mos.2024.135453, PDF,    科研立项经费支持
作者: 陈 龙：上海理工大学光电信息与计算机工程学院，上海；上海理工大学光子芯片研究院，上海；栾海涛：上海理工大学光子芯片研究院，上海
关键词: 衍射神经网络；多波长；光芯片；Diffractive Neural Network； Multi-Wavelength； Optical Chip
摘要: 随着人工智能的快速发展，传统基于电子的计算受到摩尔定律的限制。衍射神经网络作为一种新兴的技术，凭借其优越的鲁棒性，已经在许多领域得到广泛应用。在这里，我们提出了一种可以在多波长中泛用的光学衍射神经网络。该神经网络在多个波长的图像识别准确率都能保持在88%以上，为处理各种环境下的光芯片提供可能。
Abstract: With the rapid development of artificial intelligence, traditional electronic-based computation is constrained by Moore’s Law. Diffraction neural networks, as an emerging technology, have been widely applied in many fields due to their superior robustness. Here, we propose an optical diffraction neural network that can be used across multiple wavelengths. The image recognition accuracy of this neural network maintains over 88% across multiple wavelengths, providing possibilities for processing optical chips in various environments.
文章引用：陈龙, 栾海涛. 多波长二值光学衍射神经网络[J]. 建模与仿真, 2024, 13(5): 5013-5020. https://doi.org/10.12677/mos.2024.135453

参考文献

[1] Lin, X., Rivenson, Y., Yardimci, N.T., Veli, M., Luo, Y., Jarrahi, M., et al. (2018) All-Optical Machine Learning Using Diffractive Deep Neural Networks. Science, 361, 1004-1008. [Google Scholar] [CrossRef] [PubMed]
[2] Mennel, L., Symonowicz, J., Wachter, S., Polyushkin, D.K., Molina-Mendoza, A.J. and Mueller, T. (2020) Ultrafast Machine Vision with 2D Material Neural Network Image Sensors. Nature, 579, 62-66. [Google Scholar] [CrossRef] [PubMed]
[3] Teng, C., He, W., Du, W., Wu, J. and Wang, Z. (2023) Nonlinear Absorption of 2D Materials and Their Application in Optical Neural Networks. Journal of the Optical Society of America B, 40, 2007-2012. [Google Scholar] [CrossRef] 
[4] Bai, B., Li, Y., Luo, Y., Li, X., Çetintaş, E., Jarrahi, M., et al. (2023) All-Optical Image Classification through Unknown Random Diffusers Using a Single-Pixel Diffractive Network. Light: Science & Applications, 12, Article No. 69. [Google Scholar] [CrossRef] [PubMed]
[5] Traore, B.B., Kamsu-Foguem, B. and Tangara, F. (2018) Deep Convolution Neural Network for Image Recognition. Ecological Informatics, 48, 257-268. [Google Scholar] [CrossRef] 
[6] Kazanskiy, N.L., Butt, M.A. and Khonina, S.N. (2022) Optical Computing: Status and Perspectives. Nanomaterials, 12, Article 2171. [Google Scholar] [CrossRef] [PubMed]
[7] McMahon, P.L. (2023) The Physics of Optical Computing. Nature Reviews Physics, 5, 717-734. [Google Scholar] [CrossRef] 
[8] Wu, J., Lin, X., Guo, Y., Liu, J., Fang, L., Jiao, S., et al. (2022) Analog Optical Computing for Artificial Intelligence. Engineering, 10, 133-145. [Google Scholar] [CrossRef] 
[9] Zhou, J., Pu, H. and Yan, J. (2024) Spatiotemporal Diffractive Deep Neural Networks. Optics Express, 32, 1864-1877. [Google Scholar] [CrossRef] [PubMed]
[10] Barbastathis, G., Ozcan, A, Situ, G. (2019) On the Use of Deep Learning for Computational Imaging. Optica, 6, 921-943. [Google Scholar] [CrossRef] 
[11] Ozcan, A., Rivenson, Y., Wu, Y., et al. (2022) Method and System for Phase Recovery and Holographic Image Reconstruction Using a Neural Network. Google Patents US20190294108A1.
[12] Wu, Y., Rivenson, Y., Zhang, Y., Wei, Z., Günaydin, H., Lin, X., et al. (2018) Extended Depth-of-Field in Holographic Imaging Using Deep-Learning-Based Autofocusing and Phase Recovery. Optica, 5, 704-710. [Google Scholar] [CrossRef] 
[13] Almeida, V.R., Barrios, C.A., Panepucci, R.R. and Lipson, M. (2004) All-Optical Control of Light on a Silicon Chip. Nature, 431, 1081-1084. [Google Scholar] [CrossRef] [PubMed]
[14] Wetzstein, G., Ozcan, A., Gigan, S., Fan, S., Englund, D., Soljačić, M., et al. (2020) Inference in Artificial Intelligence with Deep Optics and Photonics. Nature, 588, 39-47. [Google Scholar] [CrossRef] [PubMed]
[15] Zhang, Q., Yu, H., Barbiero, M., Wang, B. and Gu, M. (2019) Artificial Neural Networks Enabled by Nanophotonics. Light: Science & Applications, 8, Article No. 42. [Google Scholar] [CrossRef] [PubMed]
[16] 成科, 胡晓楠, 贺瑜, 等. 基于光学衍射神经网络的完美涡旋光轨道角动量识别[J]. 量子电子学报, 2022, 39(2): 262-271.
[17] Heng, X., Gan, J., Zhang, Z., Li, J., Li, M., Zhao, H., et al. (2018) All-Fiber Stable Orbital Angular Momentum Beam Generation and Propagation. Optics Express, 26, 17429-17436. [Google Scholar] [CrossRef] [PubMed]
[18] Goi, E. and Gu, M. (2024) Perspective on Photonic Neuromorphic Computing. In: Gu, M., Goi, E., Wang, Y., Wan, Z., Dong, Y., Zhang, Y. and Yu, H., Eds., Neuromorphic Photonic Devices and Applications, Elsevier, 353-375. [Google Scholar] [CrossRef] 
[19] Goi, E., Schoenhardt, S. and Gu, M. (2022) Direct Retrieval of Zernike-Based Pupil Functions Using Integrated Diffractive Deep Neural Networks. Nature Communications, 13, Article No. 7532. [Google Scholar] [CrossRef] [PubMed]
[20] Qian, C., Lin, X., Lin, X., Xu, J., Sun, Y., Li, E., et al. (2020) Performing Optical Logic Operations by a Diffractive Neural Network. Light: Science & Applications, 9, Article No. 59. [Google Scholar] [CrossRef] [PubMed]
[21] Liu, C., Ma, Q., Luo, Z.J., Hong, Q.R., Xiao, Q., Zhang, H.C., et al. (2022) A Programmable Diffractive Deep Neural Network Based on a Digital-Coding Metasurface Array. Nature Electronics, 5, 113-122. [Google Scholar] [CrossRef] 
[22] Luo, X., Hu, Y., Ou, X., Li, X., Lai, J., Liu, N., et al. (2022) Metasurface-Enabled on-Chip Multiplexed Diffractive Neural Networks in the Visible. Light: Science & Applications, 11, Article No. 158. [Google Scholar] [CrossRef] [PubMed]
[23] Chen, H., Feng, J., Jiang, M., Wang, Y., Lin, J., Tan, J., et al. (2021) Diffractive Deep Neural Networks at Visible Wavelengths. Engineering, 7, 1483-1491. [Google Scholar] [CrossRef] 
[24] Xiao, H., Rasul, K. and Vollgraf, R. (2017) Fashion-MNIST: A Novel Image Dataset for Benchmarking Machine Learning Algorithms. arXiv: 170807747. [Google Scholar] [CrossRef] 

为你推荐