Laser interferometry as a robust neuromorphic platform for machine learning

2026-01-26

AI Summary

This work addresses the challenge of realizing optical neural networks with nonlinear learning capabilities and in situ trainability using only linear optical components. The authors propose a novel approach based on coherent optical states and phase encoding, wherein input information is mapped onto phase shifts to effectively induce nonlinearity within an otherwise purely linear optical circuit. By integrating the parameter-shift rule with physical backpropagation, the framework enables gradient estimation from actual optical field measurements, facilitating end-to-end in situ training. The resulting architecture exhibits high robustness against photon loss and maintains hardware simplicity while achieving, for the first time, full in situ inference and training within an entirely linear optical setup.

Technology Category

Search and Optimization: Learning to SearchComputer Vision: Learning & Optimization for CVNatural Language Processing: Learning & Optimization for NLP

Application Category

Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingResponsible Web: Machine-in-the-loop, human agency and autonomyEconomics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

We present a method for implementing an optical neural network using only linear optical resources, namely field displacement and interferometry applied to coherent states of light. The nonlinearity required for learning in a neural network is realized via an encoding of the input into phase shifts allowing for far more straightforward experimental implementation compared to previous proposals for, and demonstrations of, $\textit{in situ}$ inference. Beyond $\textit{in situ}$ inference, the method enables $\textit{in situ}$ training by utilizing established techniques like parameter shift rules or physical backpropagation to extract gradients directly from measurements of the linear optical circuit. We also investigate the effect of photon losses and find the model to be very resilient to these.

Problem

• optical neural network
• laser interferometry
• in situ training
• machine learning
• coherent states

Innovation

• optical neural network
• laser interferometry
• in situ training
• phase encoding
• linear optics