Small-scale photonic Kolmogorov-Arnold networks using standard telecom nonlinear modules

• URL: http://arxiv.org/abs/2604.08432v1
• Date: Thu, 09 Apr 2026 16:34:58 GMT
• Title: Small-scale photonic Kolmogorov-Arnold networks using standard telecom nonlinear modules
• Abstract summary: Photonic neural networks promise ultrafast inference, yet most architectures rely on linear optical meshes with electronic nonlinearities.<n>Here we introduce small-scale photonic Kolmogorov-Arnold networks (SSP-KANs) implemented entirely with standard telecommunications components.<n>SSP-KANs comprising only a few optical modules achieve strong nonlinear inference performance across classification, regression, and image recognition tasks.
• Score: 0.6219327347402195
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Photonic neural networks promise ultrafast inference, yet most architectures rely on linear optical meshes with electronic nonlinearities, reintroducing optical-electrical-optical bottlenecks. Here we introduce small-scale photonic Kolmogorov-Arnold networks (SSP-KANs) implemented entirely with standard telecommunications components. Each network edge employs a trainable nonlinear module composed of a Mach-Zehnder interferometer, semiconductor optical amplifier, and variable optical attenuators, providing a four-parameter transfer function derived from gain saturation and interferometric mixing. Despite this constrained expressivity, SSP-KANs comprising only a few optical modules achieve strong nonlinear inference performance across classification, regression, and image recognition tasks, approaching software baselines with significantly fewer parameters. A four-module network achieves 98.4\% accuracy on nonlinear classification benchmarks inaccessible to linear models. Performance remains robust under realistic hardware impairments, maintaining high accuracy down to 6-bit input resolution and 14 dB signal-to-noise ratio. By using a fully differentiable physics model for end-to-end optimisation of optical parameters, this work establishes a practical pathway from simulation to experimental demonstration of photonic KANs using commodity telecom hardware.

Related papers

• Low-power analogue neural networks with trainable nonlinear connections for continuous control [54.59241649882409]
  Physical neural networks promise low-power machine learning by computing directly with analogue device physics.<n>We place trainable nonlinear functions on the connections, making each physical connection a learnable computational element.<n>We find that the benefit is task-dependent and follows from the smoothness of the physical basis.
  arXiv  Detail & Related papers  (2026-06-21T15:55:23Z)
• Breaking the Cascade: Compact Nonlinear Optical Computing with Single-Layer Encoder-Decoder Co-Localization [40.4197846036432]
  nonlinear computing can be achieved with a single linear diffractive surface under coherent illumination.<n>We introduce a compact encoder-decoder co-localization architecture in which an input-dependent dynamic encoder and a static optimized decoder are integrated.<n>We experimentally validate the proposed approach using a visible-light optical set-up trained through in situ learning.
  arXiv  Detail & Related papers  (2026-05-31T05:46:10Z)
• Optical Neural Networks from Coherent Transient Dynamics in Waveguide QED [0.0]
  Optical neural networks promise ultrafast, low-energy information processing by performing computation directly with photons.<n>We propose an all-optical fully connected neural network architecture in which the basic neuronal functions are realized by coherent quantum dynamics.<n>Full-physics simulations demonstrate high classification accuracy on MNIST and colored-object recognition tasks.
  arXiv  Detail & Related papers  (2026-05-18T02:11:34Z)
• Relay-Assisted Activation-Integrated SIM for Wireless Physical Neural Networks [53.64687377045908]
  Wireless physical neural networks (WPNNs) have emerged as a promising paradigm for performing neural computation directly in the physical layer of wireless systems.<n>We propose a relay-assisted WPNN architecture based on activation-integrated stacked intelligent metasurfaces (AI-SIMs)
  arXiv  Detail & Related papers  (2026-04-05T18:07:13Z)
• ReDON: Recurrent Diffractive Optical Neural Processor with Reconfigurable Self-Modulated Nonlinearity [4.488347887618485]
  We introduce the Recurrent Diffractive Optical Neural Processor (ReDON), a novel architecture featuring reconfigurable, recurrent self-modulated nonlinearity.<n>Inspired by the gated linear unit (GLU) used in large language models, ReDON senses a fraction of the propagating optical field and modulates its phase or intensity via a lightweight parametric function.<n>On image recognition and segmentation benchmarks, ReDON improves test accuracy and mean intersection-over-union (mIoU) by up to 20% compared with prior DONNs.
  arXiv  Detail & Related papers  (2026-02-27T02:49:05Z)
• Integrated polarization-entangled photon source for wavelength-multiplexed quantum networks [49.82426139329382]
  We present a simple yet high-performance on-chip polarization-entangled photon-pair source on thin-film lithium niobate (TFLN)<n>Our device employs dual quasi-phase matching (D-QPM) that sequentially supports type-0 and type-I spontaneous parametric down-conversion in a single nanophotonic waveguide.<n>We realize wavelength-multiplexed entanglement distribution in a four-user quantum network deployed over metropolitan fiber links up to 50 km.
  arXiv  Detail & Related papers  (2025-11-27T18:30:01Z)
• 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)
• Unconventional Computing based on Four Wave Mixing in Highly Nonlinear Waveguides [0.0]
  We numerically analyze a photonic unconventional accelerator based on the four-wave mixing effect in highly nonlinear waveguides. By exploiting the rich Kerr-induced nonlinearities, multiple nonlinear transformations of an input signal can be generated and used for solving complex nonlinear tasks.
  arXiv  Detail & Related papers  (2024-02-14T12:34:38Z)
• All-optical modulation with single-photons using electron avalanche [66.27103948750306]
  We demonstrate all-optical modulation enabled by electron avalanche process in silicon.<n>Our approach opens the possibility of gigahertz-speed, and potentially even faster, optical switching at the single-photon level.
  arXiv  Detail & Related papers  (2023-12-18T20:14:15Z)
• 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)
• All-optical graph representation learning using integrated diffractive photonic computing units [51.15389025760809]
  Photonic neural networks perform brain-inspired computations using photons instead of electrons. We propose an all-optical graph representation learning architecture, termed diffractive graph neural network (DGNN) We demonstrate the use of DGNN extracted features for node and graph-level classification tasks with benchmark databases and achieve superior performance.
  arXiv  Detail & Related papers  (2022-04-23T02:29:48Z)
• 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)

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.