ReDON: Recurrent Diffractive Optical Neural Processor with Reconfigurable Self-Modulated Nonlinearity

2026-02-27

AI Summary

This work proposes ReDON, a novel reconfigurable diffractive optical neural network architecture that overcomes the limitations of conventional DONNs—namely, their reliance on static passive phase masks and lack of efficient nonlinearity and reconfigurability, which constrain representational capacity. ReDON uniquely integrates a recurrent structure with an input-dependent self-modulating nonlinearity inspired by gating mechanisms in large language models, enabling dynamic optical-domain modulation. By combining electro-optic self-modulation with a fixed metasurface, the approach achieves adaptive control of both phase and amplitude of the optical field through lightweight parametric functions, without increasing hardware complexity. Evaluated on image classification and segmentation tasks, ReDON improves accuracy and mean Intersection-over-Union (mIoU) by up to 20% over existing DONN methods while incurring negligible additional power consumption.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Non-convex Optimization
• Machine Learning: Deep Neural Architectures and Foundation Models

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Diffractive optical neural networks (DONNs) have demonstrated unparalleled energy efficiency and parallelism by processing information directly in the optical domain. However, their computational expressivity is constrained by static, passive diffractive phase masks that lack efficient nonlinear responses and reprogrammability. To address these limitations, we introduce the Recurrent Diffractive Optical Neural Processor (ReDON), a novel architecture featuring reconfigurable, recurrent self-modulated nonlinearity. This mechanism enables dynamic, input-dependent optical transmission through in-situ electro-optic self-modulation, providing a highly efficient and reprogrammable approach to optical computation. Inspired by the gated linear unit (GLU) used in large language models, ReDON senses a fraction of the propagating optical field and modulates its phase or intensity via a lightweight parametric function, enabling effective nonlinearity with minimal inference overhead. As a non-von Neumann architecture in which the primary weighting elements (metasurfaces) remain fixed, ReDON substantially extends the nonlinear representational capacity and task adaptability of conventional DONNs through recurrent optical hardware reuse and dynamically tunable nonlinearity. We systematically investigate various self-modulation configurations to characterize the trade-offs between hardware efficiency and computational expressivity. On image recognition and segmentation benchmarks, ReDON improves test accuracy and mean intersection-over-union (mIoU) by up to 20% compared with prior DONNs employing either optical or digital nonlinearities at comparable model complexity and negligible additional power consumption. This work establishes a new paradigm for reconfigurable nonlinear optical computing, uniting recurrence and self-modulation within non-von Neumann analog processors.

Problem

• diffractive optical neural networks
• nonlinearity
• reconfigurability
• computational expressivity
• optical computing

Innovation

• Recurrent diffractive optics
• Self-modulated nonlinearity
• Reconfigurable optical computing
• Non-von Neumann architecture
• Electro-optic modulation