Passive All-Optical Nonlinear Neuron Activation via PPLN Nanophotonic Waveguides

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 on PICs. Here, we demonstrate a compact and readily integrated all-optical nonlinear activation function, experimentally realized through highly pump-depleted second-harmonic generation (SHG) in periodically poled lithium niobate (PPLN) nanophotonic waveguides, achieving 79% absolute conversion efficiency. This activation exhibits a sigmoid-like, wavelength-selective response with femtosecond-scale dynamics and light-speed processing, requiring no electrical control or auxiliary optical signals. We further validate its feasibility for neural inference by combining the measured SHG-based nonlinearity with linear operations implemented via a Mach-Zehnder interferometer system on a silicon PIC. Our demonstration achieves 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.