Laser interferometry as a robust neuromorphic platform for machine learning

• URL: http://arxiv.org/abs/2601.18047v2
• Date: Fri, 30 Jan 2026 13:48:48 GMT
• Title: Laser interferometry as a robust neuromorphic platform for machine learning
• Authors: Amanuel Anteneh, Kyungeun Kim, J. M. Schwarz, Israel Klich, Olivier Pfister,
• Abstract summary: We present a method for implementing an optical neural network using only linear optical resources.<n>The nonlinearity required for learning in a neural network is realized via an encoding of the input into phase shifts.
• Score: 1.3831855739681835
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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, $\textit{in situ}$ inference. Beyond $\textit{in situ}$ inference, the method enables $\textit{in situ}$ training by utilizing established techniques like parameter shift rules 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.

Related papers

• Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit Acceleration [67.12978375116599]
  We show that the steps of gradient descent (GD) reduce to those of generalized perceptron algorithms.<n>This helps explain the optimization dynamics and the implicit acceleration phenomenon observed in neural networks.
  arXiv  Detail & Related papers  (2025-12-12T14:16:35Z)
• Noise-tolerant tomography of multimode linear optical interferometers with single photons [0.0]
  We present the method for reconstructing the transfer matrix of a linear optical interferometer.<n>Our approach accounts for losses and photon indistinguishability, making it robust to experimental imperfections.<n>The results show high fidelity in matrix reconstruction and successful application in boson sampling experiments.
  arXiv  Detail & Related papers  (2025-06-25T14:36:38Z)
• Gradients of unitary optical neural networks using parameter-shift rule [14.364214412875494]
  This paper explores the application of the parameter-shift rule (PSR) for computing gradients in unitary optical neural networks (UONNs)<n>We demonstrate how PSR, which calculates gradients by evaluating functions at shifted parameter values, can be effectively adapted for training UONNs constructed from Mach-Zehnder interferometer meshes.<n>We present the theoretical framework and practical methodology for applying PSR to optimize phase parameters in optical neural networks, potentially advancing the development of efficient hardware-based training strategies for optical computing systems.
  arXiv  Detail & Related papers  (2025-06-13T08:21:06Z)
• Certified Neural Approximations of Nonlinear Dynamics [51.01318247729693]
  In safety-critical contexts, the use of neural approximations requires formal bounds on their closeness to the underlying system.<n>We propose a novel, adaptive, and parallelizable verification method based on certified first-order models.
  arXiv  Detail & Related papers  (2025-05-21T13:22:20Z)
• Nonlinear Computation with Linear Optics via Source-Position Encoding [0.0]
  We introduce a novel method to achieve nonlinear computation in fully linear media.<n>Our method can operate at low power and requires only the ability to drive the optical system at a data-dependent spatial position.<n>We formulate a fully automated, topology-optimization-based hardware design framework for extremely specialized optical neural networks.
  arXiv  Detail & Related papers  (2025-04-29T03:55:05Z)
• Generalizable Non-Line-of-Sight Imaging with Learnable Physical Priors [52.195637608631955]
  Non-line-of-sight (NLOS) imaging has attracted increasing attention due to its potential applications. Existing NLOS reconstruction approaches are constrained by the reliance on empirical physical priors. We introduce a novel learning-based solution, comprising two key designs: Learnable Path Compensation (LPC) and Adaptive Phasor Field (APF)
  arXiv  Detail & Related papers  (2024-09-21T04:39:45Z)
• Globally Optimal Training of Neural Networks with Threshold Activation Functions [63.03759813952481]
  We study weight decay regularized training problems of deep neural networks with threshold activations. We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
  arXiv  Detail & Related papers  (2023-03-06T18:59:13Z)
• Retrieving space-dependent polarization transformations via near-optimal quantum process tomography [55.41644538483948]
  We investigate the application of genetic and machine learning approaches to tomographic problems. We find that the neural network-based scheme provides a significant speed-up, that may be critical in applications requiring a characterization in real-time. We expect these results to lay the groundwork for the optimization of tomographic approaches in more general quantum processes.
  arXiv  Detail & Related papers  (2022-10-27T11:37:14Z)
• Physics-aware Differentiable Discrete Codesign for Diffractive Optical Neural Networks [12.952987240366781]
  This work proposes a novel device-to-system hardware-software codesign framework, which enables efficient training of Diffractive optical neural networks (DONNs) Gumbel-Softmax is employed to enable differentiable discrete mapping from real-world device parameters into the forward function of DONNs. The results have demonstrated that our proposed framework offers significant advantages over conventional quantization-based methods.
  arXiv  Detail & Related papers  (2022-09-28T17:13:28Z)
• Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces [103.08512487830669]
  This paper presents an uncalibrated deep neural network framework for the photometric stereo problem. Existing neural network-based methods either require exact light directions or ground-truth surface normals of the object or both. We propose an uncalibrated neural inverse rendering approach to this problem.
  arXiv  Detail & Related papers  (2020-12-12T10:33:08Z)
• Rapid characterisation of linear-optical networks via PhaseLift [51.03305009278831]
  Integrated photonics offers great phase-stability and can rely on the large scale manufacturability provided by the semiconductor industry. New devices, based on such optical circuits, hold the promise of faster and energy-efficient computations in machine learning applications. We present a novel technique to reconstruct the transfer matrix of linear optical networks.
  arXiv  Detail & Related papers  (2020-10-01T16:04:22Z)
• Efficient trainability of linear optical modules in quantum optical neural networks [0.0]
  We show that coherent light in $m$ modes can be generically compiled efficiently if the total intensity scales sublinearly with $m$. We further demonstrate efficient trainability of $m$ mode linear optical quantum circuits for variational mean field energy estimation of positive quadratic Hamiltonians for input states that do not have energy exponentially vanishing with $m$.
  arXiv  Detail & Related papers  (2020-08-20T19:26:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.