PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 7, 2026eLight3 citationsOpen Access

Passive all-optical nonlinear neuron activation via PPLN nanophotonic waveguides

WFWujie FuXSXiaodong ShiSMSakthi Sanjeev Mohanraj

Key Points

  • To develop a passive, all-optical nonlinear activation method using PPLN waveguides for neural networks.
  • Experimentally tested nonlinear activation in periodically poled lithium niobate (PPLN) nanophotonic waveguides.
  • Achieved approximately 80% absolute conversion efficiency.
  • Cascaded PPLN activations with a linear silicon photonic integrated circuit (PIC) for neural inference.
  • Successfully demonstrated sigmoid-like response in nonlinear activation with femtosecond-scale dynamics.
  • PPLN-based activations showed potential performance comparable to digital neural network implementations in real-world tasks.
  • Enabled scalable, high-speed optical neural networks for future photonic AI hardware.

Abstract

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.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Fu et al. (2026) studied this question.

synapsesocial.com/papers/69abc2615af8044f7a4ebea7https://doi.org/10.1186/s43593-026-00125-0
Ask AI
Helpful
Bookmark
Share
View Full Paper