Application of a digital micromirror device in diffractive optical neural networks: space-time characteristics and limitations

Digital micromirror devices are widely used for optical processing of graphic information, including for the purpose of building holographic display systems and adaptive formation of light beams. Modulators are also used in the creation of diffraction neuron-like systems. The demand for modulators of this type is due to the unique combination of high switching speed and high spatial resolution for optical systems. This paper presents the results of an experimental study of the HDSLM54D67 digital micromirror device (UPO Labs, China), which, according to the manufacturer, has advanced characteristics for its type. The true values of its spatial and velocity parameters are estimated by displaying binary computer-synthesized Fourier holograms and two-dimensional distributions in the form of geometric primitives. The results revealed an abnormal modulation of the left half of the micromirror matrix, leading to a parasitic doubling of the images reconstructed from the holograms. The analysis of the causes of these distortions was carried out, and their connection with the features of the modulator control unit was revealed. The limitations of the applicability of this digital micromirror device model are determined in accordance with the identifi ed spatial limitations (using only the half of the micromirror matrix with a resolution of 1358×1600 pixels) and proposals for optimal integration of the modulator into an optical system are formulated. The use of a modulator is possible, but theoretically the maximum bandwidth will be reduced by 2 times. The results of the study can be used in further optical experiments with this digital micromirror device, including for the task of constructing a diffraction neural network.

1. Lecun Y., Bottou L., Bengio Y., Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(5), 2278–2324 (1998). https://doi.org/10.1109/5.726791

2. Lu Z., Sreekumar G., Goodman E., Banzhaf W., Deb K., Boddeti V. N. Neural architecture transfer. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(9), 2971–2989 (2021). https://doi.org/10.1109/TPAMI.2021.3052758

3. Ruiz L., Gama F., Ribeiro A. Graph neural networks: architectures, stability and transferability. Proceedings of the IEEE, 109(5), 660–682 (2021). https://doi.org/10.1109/JPROC.2021.3055400

4. Ahmed S., Dera D., Hassan S., Bouaynaya N., Rasool G. Failure detection in deep neural networks for medical imaging. Frontiers in Medical Technology, 4, 919046 (2022). https://doi.org/10.3389/fmedt.2022.919046

5. Svistunov A. S., Rymov D. A., Starikov R. S., Cheremkhin P. A. HoloForkNet: digital hologram reconstruction via multibranch neural network. Applied Sciences, 13(10), 6125 (2023). https://doi.org/10.3390/app13106125 ; https://elibrary.ru/hmhhws

6. Borylo P., Biernacka E., Domzal J., Kądziołka B., Kantor M., Rusek K., Skala M., Wajda K., Wójcik R., Zabek W. Neural networks in selected aspects of communications and networking. IEEE Access, 12, 132856–132890 (2024). https://doi.org/10.1109/ACCESS.2024.3404866

7. Poyser M., Breckon T. Neural architecture search: a contemporary literature review for computer vision applications. Pattern Recognition, 147, 110052 (2023). https://doi.org/10.1016/j.patcog.2023.110052

8. Rymov D. A., Svistunov A. S., Starikov R. S., Shifrina A. V., Rodin V. G., Evtikhiev N. N., Cheremkhin P. A. 3D-CGH-Net: customizable 3D-hologram generation via deep learning. Optics and Lasers in Engineering, 184, 108645 (2025). https://doi.org/10.1016/j.optlaseng.2024.108645 ; https://elibrary.ru/judnpo

9. Collobert R., Weston J. A unifi ed architecture for natural language processing: deep neural networks with multitask learning. Proceedings of the 25th International Conference on Machine Learning, Helsinki, Finland, July 5–9, pp. 160–167 (2008). https://doi.org/10.1145/1390156.1390177

10. Galke L., Ram Y., Raviv L. Deep neural networks and humans both benefi t from compositional language structure. Nature Communications, 15, 10816 (2024). https://doi.org/10.1038/s41467-024-55158-1

11. Dennard R.H., Gaensslen F. H., Yu H.-N., Rideovt V., Bassous E., LeBlanc A. R. Design of ion-implanted MOSFET’s with very small physical dimensions. IEEE Solid-State Circuits Society Newsletter, 12(1), 38–50 (2007). https://doi.org/10.1109/N-SSC.2007.4785543

12. Zhang D., Tan Z. A review of optical neural networks. Applied Sciences, 12, 5338 (2022). https://doi.org/10.3390/app12115338

13. Yang D., Lei Z., Li L., Shen W., Li H., Gui C., Song Y. High optical storage density using three-dimensional hybrid nanostructures based on machine learning. Optics and Lasers in Engineering, 161, 107347 (2022). https://doi.org/10.1016/j.optlaseng.2022.107347

14. Hamerly R., Bernstein L., Sludds A., Soljačić M., Englund D. Large-scale optical neural networks based on photoelectric multiplication. Physical Review X, 9, 021032 (2019). https://doi.org/10.1103/PhysRevX.9.021032

15. Mengu D., Luo Y., Rivenson Y., Ozcan A. Analysis of diffractive optical neural networks and their integration with electronic neural networks. IEEE Journal of Selected Topics in Quantum Electronics, 26, 1–14 (2020). https://doi.org/10.1109/JSTQE.2019.2921376

16. Xu R., Lv P., Xu F., Shi Y. A survey of approaches for implementing optical neural networks. Optics & Laser Technology, 136, 106787 (2021). https://doi.org/10.1016/j.optlastec.2020.106787

17. Song M., Li R., Wang J. Only frequency domain diffractive deep neural networks. Applied Optics, 62, 1082–1087 (2023). https://doi.org/10.1364/AO.480640

18. Wu K., Liu Y., Gao H., Tao J., Xiong W., Li X. Effi cient design optimization for diffractive deep neural networks. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 44(3), 1199–1203 (2025). https://doi.org/10.1109/TCAD.2024.3432632

19. Li B., Zhu Y., Fei J., Zheng R., Gu M., Jian L. Multi-functional broadband diffractive neural network with a single spatial light modulator. APL Photonics, 10, 016115 (2025). https://doi.org/10.1063/5.0245832

20. Zheng M., Liu W., Shi L., Zi J. Diffractive neural networks with improved expressive power for grayscale image classifi cation. Photonics Research, 12, 1159–1166 (2024) https://doi.org/10.1364/PRJ.513845

21. Minikhanov T. Z., Zlokazov E. Yu., Starikov R. S., Cheremkhin P. A. Phase modulation time dynamics of the liquid-crystal spatial light modulator. Izmeritel’naya Tekhnika, (12), 35–39 (2023). (In Russ.). https://doi.org/10.32446/0368-1025it.2023-12-35-39 ; https://elibrary.ru/spyvls

22. Hu Z., Miscuglio M., Li S., George J., Gupta P., Sorger V. J. Electro-optical hybrid Fourier neural network with amplitudeonly modulation. In Frontiers in Optics / Laser Science, B. Lee, C. Mazzali, K. Corwin, and R. Jason Jones, eds., OSA Technical Digest, FM7D.3. Optica Publishing Group (2020). https://doi.org/10.1364/FIO.2020.FM7D.3

23. Kiriy S. A., Svistunov A. S., Rymov D. A., Starikov R. S., Shifrina A. V., Cheremkhin P. A. Object image reconstruction: method for reconstructing images from digital off-axis holograms using a generative adversarial network. Izmeritel’naya Tekhnika, 73(4), 23–31 (2024). (In Russ.). https://doi.org/10.32446/0368-1025it.2024-4-23-31 ; https://elibrary.ru/potyoh

24. Turtaev S., Leite I. T., Mitchell K. J., Padgett M. J., Phillips D. B., Čižmár T. Exploiting digital micromirror device for holographic micro-endoscopy. Proceedings of SPIE, 10932, 1093203 (2019). https://doi.org/10.1117/12.2509429

25. Wang T., Sohoni M. M., Ma S-Y., Wright L. G., Onodera T., Stein M. M., Anderson M., Richard B. C., McMahon P. L. Applications of digital micromirror devices in photonic neural networks. Proceedings of SPIE, PC12435, PC1243501 (2023). https://doi.org/10.1117/12.2649385

26. Volkov A. A., Minikhanov T. Z., Zlokazov E. Yu., Shifrina A. V., Petrova E. K., Starikov R. S. Characteristics of temporal dynamics of liquid crystal spatial modulators as a performance limitation of tunable diffractive neural networks. Izmeritel’naya Tekhnika, 74(1), 83–89 (2025). (In Russ.). https://doi.org/10.32446/0368-1025it.2025-1-83-89 ; https://elibrary.ru/asgugk

27. Ovchinnikov A. S., Volkov A. A., Kerov A. A. Shifrina A. V., Petrova E. K., Cheremkhin P. A. Development of a universal method for quantization of computer-generated holograms in the optical image reconstruction. Izmeritel’naya Tekhnika, 74(2), 70–77 (2025). (In Russ.). https://doi.org/10.32446/0368-1025it.2025-2-70-77 ; https://elibrary.ru/fmgmth

28. Ivanova S. D., Shemonaev D. D. Image reconstruction with the use of fresnel holograms: relationship between the longitudinal and transverse scales of images. Izmeritel’naya Tekhnika, 73(5), 35–40 (2024). (In Russ.). https://doi.org/10.32446/0368-1025it.2024-5-35-40 ; https://elibrary.ru/wectmt

29. Akhter N., Min G., Kim J., Lee B. H. A comparative study of reconstruction algorithms in digital holography. Optik, 124, 2955–2958 (2013). https://doi.org/10.1016/j.ijleo.2012.09.002

30. Otsu N. A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1), 62–66 (1979). https://doi.org/10.1109/TSMC.1979.4310076

31. Scholes S., Kara R., Pinnell J., Rodríguez-Fajardo V., Forbes A. Structured light with digital micromirror devices: a guide to best practice. Optical Engineering, 59(4), 041202 (2019). https://doi.org/10.1117/1.OE.59.4.041202.