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

arXiv: https://arxiv.org/abs/2604.08432 · HTML: https://mlsanity.com/paper/2604.08432/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 30 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Builds on (most cited first, 4 of 4)

- [Photonics for artificial intelligence and neuromorphic computing](https://mlsanity.com/paper/2011.00111/) (2020)
- [The physics of optical computing](https://mlsanity.com/paper/2308.00088/) (2023)
- [Photonic tensor cores for machine learning](https://mlsanity.com/paper/2002.03780/) (2020)
- [Neural Networks-based Equalizers for Coherent Optical Transmission: Caveats and Pitfalls](https://mlsanity.com/paper/2109.14942/) (2021)

## Built on by (most cited first, 1 of 1)

- [Low-power analogue neural networks with trainable nonlinear connections for continuous control](https://mlsanity.com/paper/2606.23742/) (2026)

## Abstract (arXiv)

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 the constrained functional form of these optical nonlinearities, 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 94.3% (IQR: 90.3--97.4%, 10~seeds) accuracy on nonlinear classification benchmarks; a seven-module network attains R2 = 0.986 ± 0.015 on six-input regression. 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.