mlsanityData to 14 Oct 2026

All-Optical Machine Learning Using Diffractive Deep Neural Networks

arXiv 1804.08711 ↗First posted 14 Apr 2018cs.NE cs.LG physics.comp-phcited by 177

Not on the map. Why?

Abstract (arXiv)

We introduce an all-optical Diffractive Deep Neural Network (D2NN) architecture that can learn to implement various functions after deep learning-based design of passive diffractive layers that work collectively. We experimentally demonstrated the success of this framework by creating 3D-printed D2NNs that learned to implement handwritten digit classification and the function of an imaging lens at terahertz spectrum. With the existing plethora of 3D-printing and other lithographic fabrication methods as well as spatial-light-modulators, this all-optical deep learning framework can perform, at the speed of light, various complex functions that computer-based neural networks can implement, and will find applications in all-optical image analysis, feature detection and object classification, also enabling new camera designs and optical components that can learn to perform unique tasks using D2NNs.

Key facts. Cited by 177 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 17; 2022: 46; 2023: 27; 2024: 32; 2025: 24; 2026: 31.

177 papers.

Sort:

By area:

  1. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  2. 2021Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systemscited by 128
  3. 2024Training of Physical Neural Networkscited by 49
  4. 2023Backpropagation-free Training of Deep Physical Neural Networkscited by 42
  5. 2021Vector Symbolic Architectures as a Computing Framework for Emerging Hardwarecited by 35
  6. 2021Applications and Techniques for Fast Machine Learning in Sciencecited by 32
  7. 2021An optical neural network using less than 1 photon per multiplicationcited by 30
  8. 2022Image sensing with multilayer, nonlinear optical neural networkscited by 25
  9. 2021All-Optical Synthesis of an Arbitrary Linear Transformation Using Diffractive Surfacescited by 24
  10. 2022Diffractive all-optical computing for quantitative phase imagingcited by 22
  11. 2022To image, or not to image: Class-specific diffractive cameras with all-optical erasure of undesired objectscited by 21
  12. 2023Nonlinear Processing with Linear Opticscited by 20
38 more
  1. 2023On the use of deep learning for phase recoverycited by 20
  2. 2023Forward-Forward Training of an Optical Neural Networkcited by 19
  3. 2021An extended physics informed neural network for preliminary analysis of parametric optimal control problemscited by 16
  4. 2022Snapshot Multispectral Imaging Using a Diffractive Optical Networkcited by 16
  5. 2022Hybrid training of optical neural networkscited by 15
  6. 2023Nonlinear optical encoding enabled by recurrent linear scatteringcited by 15
  7. 2025A multi-agentic framework for real-time, autonomous freeform metasurface designcited by 14
  8. 2021A compact butterfly-style silicon photonic-electronic neural chip for hardware-efficient deep learningcited by 13
  9. 2022Super-resolution image display using diffractive decoderscited by 13
  10. 2022Unidirectional Imaging using Deep Learning-Designed Materialscited by 13
  11. 2022Single-Shot Optical Neural Networkcited by 12
  12. 2023Spatially Varying Nanophotonic Neural Networkscited by 12
  13. 2022Polarization Multiplexed Diffractive Computing: All-Optical Implementation of a Group of Linear Transformations Through a Polarization-Encoded Diffractive Networkcited by 10
  14. 2023Optical Transformerscited by 10
  15. 2023Multispectral Quantitative Phase Imaging Using a Diffractive Optical Networkcited by 10
  16. 2022Dual adaptive training of photonic neural networkscited by 9
  17. 2023Photonic Advantage of Optical Encoderscited by 8
  18. 2023Quantum-limited stochastic optical neural networks operating at a few quanta per activationcited by 8
  19. 2023All-Optical Phase Conjugation Using Diffractive Wavefront Processingcited by 8
  20. 2024Optical Generative Modelscited by 8
  21. 2023Training neural networks with end-to-end optical backpropagationcited by 7
  22. 2025Over-the-Air Edge Inference via End-to-End Metasurfaces-Integrated Artificial Neural Networkscited by 7
  23. 2021Knowledge Distillation Circumvents Nonlinearity for Optical Convolutional Neural Networkscited by 6
  24. 2021Wave-based extreme deep learning based on non-linear time-Floquet entanglementcited by 6
  25. 2022All-optical graph representation learning using integrated diffractive photonic computing unitscited by 6
  26. 2022Diffractive Interconnects: All-Optical Permutation Operation Using Diffractive Networkscited by 6
  27. 2022Intelligent Computing: The Latest Advances, Challenges and Futurecited by 6
  28. 2023All-optical image denoising using a diffractive visual processorcited by 6
  29. 2024Information hiding cameras: optical concealment of object information into ordinary imagescited by 6
  30. 2021Classification and reconstruction of spatially overlapping phase images using diffractive optical networkscited by 5
  31. 2022Deep Optical Coding Design in Computational Imagingcited by 5
  32. 2022Photonic Reconfigurable Accelerators for Efficient Inference of CNNs with Mixed-Sized Tensorscited by 5
  33. 2022All-optical image classification through unknown random diffusers using a single-pixel diffractive networkcited by 5
  34. 2022Physics-aware Differentiable Discrete Codesign for Diffractive Optical Neural Networkscited by 5
  35. 2022Optical multi-task learning using multi-wavelength diffractive deep neural networkscited by 5
  36. 2024Training all-mechanical neural networks for task learning through in situ backpropagationcited by 5
  37. 2024Minimalist Vision with Freeform Pixelscited by 5
  38. 2025Universal Approximation with XL MIMO Systems: OTA Classification via Trainable Analog Combiningcited by 5

50 most cited of 177 All 177 (JSON)