Passive All-Optical Nonlinear Neuron Activation via PPLN Nanophotonic Waveguides

Abstract

Artificial intelligence (AI) is transforming modern life, yet the growing scale of AI applications places mounting demands on computational resources, raising sustainability concerns. Photonic integrated circuits (PICs) offer a promising alternative, enabling massive parallelism, low latency, and reduced electrical overhead, particularly excelling in high-throughput linear operations. However, passive and fully optical nonlinear activation functions with equally superb performance remain rare, posing a critical bottleneck in realizing all-optical neural networks in PICs. Here, we demonstrate a compact and integrated all-optical nonlinear activation method, experimentally realized through strong second-order optical nonlinearities in periodically poled lithium niobate (PPLN) nanophotonic waveguides, achieving 80% absolute conversion efficiency. This activation exhibits a sigmoid-like, wavelength-selective response with femtosecond-scale dynamics and light-speed processing, operating passively without external control and auxiliary signals. We validate its feasibility for neural inference by cascading the PPLN-driven activations with a linear silicon PIC, demonstrating all-optical nonlinear neuron expressivity. Moreover, combining the measured nonlinearity with linear operations calculated by the PIC, we show that PPLN-activated multi-layer optical neural networks can achieve performance on par with digital implementations in real-world tasks, including airfoil regression and medical image classification. These results pave the way toward scalable, high-speed, and fully integrated all-optical neural networks for next-generation photonic AI hardware.

Has been published on eLight 6, 9 (2026). https://doi.org/10.1186/s43593-026-00125-0

References in corpus (17)

• Deep Learning with Coherent Nanophotonic Circuits
• Parallel convolution processing using an integrated photonic tensor core
• Photonics for artificial intelligence and neuromorphic computing
• Integrated photonics on thin-film lithium niobate
• High-Performance Hybrid Silicon and Lithium Niobate Mach-Zehnder Modulators for 100 Gbit/s and Beyond
• MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification
• Single-chip photonic deep neural network for instantaneous image classification
• Ultrahigh-efficiency second-harmonic generation in nanophotonic PPLN waveguides
• The physics of optical computing
• Experimentally realized in situ backpropagation for deep learning in nanophotonic neural networks
• Single chip photonic deep neural network with accelerated training
• Survey of Machine Learning Accelerators
• Efficient photon-pair generation in layer-poled lithium niobate nanophotonic waveguides
• SineKAN: Kolmogorov-Arnold Networks Using Sinusoidal Activation Functions
• Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasets
• All-optical nonlinear activation function based on stimulated Brillouin scattering
• Massively parallel and universal approximation of nonlinear functions using diffractive processors