mlsanityData to 7 Oct 2026

Laser interferometry as a robust neuromorphic platform for machine learning

arXiv 2601.18047 ↗First posted 26 Jan 2026physics.optics cs.ET cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We present a method for implementing an optical neural network using only linear optical resources, namely field displacement and interferometry applied to coherent states of light. The nonlinearity required for learning in a neural network is realized via an encoding of the input into phase shifts allowing for far more straightforward experimental implementation compared to previous proposals for, and demonstrations of, textitin situ inference. Beyond textitin situ inference, the method enables textitin situ training by utilizing established techniques like parameter shift methods or physical backpropagation to extract gradients directly from measurements of the linear optical circuit. We also investigate the effect of photon losses and find the model to be very resilient to these.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 38 of its 86 references that are in the map. First posted on arXiv 26 Jan 2026.

Builds on

38 of 86 references.

References · 38

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2024The Llama 3 Herd of Modelscited by 14,192
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  7. 2025Qwen3 Technical Reportcited by 8,195
  8. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  9. 2020GLU Variants Improve Transformercited by 1,724
  10. 2016Language Modeling with Gated Convolutional Networkscited by 688
  11. 2023A Comprehensive Overview of Large Language Modelscited by 639
  12. 2024Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inferencecited by 527
26 more
  1. 2016Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagationcited by 251
  2. 2021Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systemscited by 125
  3. 2018Continuous-variable quantum neural networkscited by 74
  4. 2016Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNscited by 62
  5. 2019Stochastic gradient descent for hybrid quantum-classical optimizationcited by 59
  6. 2024Training of Physical Neural Networkscited by 47
  7. 2018Training of photonic neural networks through in situ backpropagationcited by 45
  8. 2022Experimentally realized in situ backpropagation for deep learning in nanophotonic neural networkscited by 43
  9. 2019Wave Physics as an Analog Recurrent Neural Networkcited by 42
  10. 2023Backpropagation-free Training of Deep Physical Neural Networkscited by 42
  11. 2021An optical neural network using less than 1 photon per multiplicationcited by 30
  12. 2021Self-learning Machines based on Hamiltonian Echo Backpropagationcited by 28
  13. 2017Vowel recognition with four coupled spin-torque nano-oscillatorscited by 22
  14. 2019Reprogrammable Electro-Optic Nonlinear Activation Functions for Optical Neural Networkscited by 19
  15. 2023Forward-Forward Training of an Optical Neural Networkcited by 19
  16. 2023Nonlinear Processing with Linear Opticscited by 19
  17. 2024Training Coupled Phase Oscillators as a Neuromorphic Platform using Equilibrium Propagationcited by 16
  18. 2023Nonlinear optical encoding enabled by recurrent linear scatteringcited by 14
  19. 2022Frequency propagation: Multi-mechanism learning in nonlinear physical networkscited by 11
  20. 2022Learning by non-interfering feedback chemical signaling in physical networkscited by 10
  21. 2024Arbitrary control over multimode wave propagation for machine learningcited by 9
  22. 2024Quantum Equilibrium Propagation: Gradient-Descent Training of Quantum Systemscited by 9
  23. 2024Quantum Equilibrium Propagation for efficient training of quantum systems based on Onsager reciprocitycited by 9
  24. 2016Superconducting optoelectronic circuits for neuromorphic computingcited by 6
  25. 2023A universal approximation theorem for nonlinear resistive networkscited by 5
  26. 2024Training all-mechanical neural networks for task learning through in situ backpropagationcited by 4

Built on by

Not cited yet.