Large-scale photonic computing with nonlinear disordered media

TL;DR

This paper introduces a large-scale photonic neural network using disordered lithium niobate media that leverages optical nonlinearities and scattering for efficient, high-performance machine learning tasks.

Contribution

It demonstrates a novel scalable nonlinear photonic neural system based on disordered media, enabling complex computations with improved performance over linear systems.

Findings

Achieved up to 27,648 input and 3,500 nonlinear output nodes.

Showed enhanced performance in image, regression, and graph classification tasks.

Utilized second-harmonic generation as nonlinear activation in a disordered photonic medium.

Abstract

Neural networks find widespread use in scientific and technological applications, yet their implementations in conventional computers have encountered bottlenecks due to ever-expanding computational needs. Photonic neuromorphic hardware, which manipulates information and represents data continuously in the optical domain, is one of the promising platforms with potential advantages of massive parallelism, ultralow latency, and reduced energy consumption. While linear photonic neural networks are within reach, photonic computing with large-scale optical nonlinear nodes remains largely unexplored. Here, we demonstrate a large-scale, high-performance nonlinear photonic neural system based on a disordered polycrystalline slab composed of lithium niobate nanocrystals. Mediated by random quasi-phase-matching and multiple scattering, linear and nonlinear optical speckle features are generated as the interplay between the simultaneous linear random scattering and the second-harmonic generation, defining a complex neural network in which the second-order nonlinearity acts as internal nonlinear activation functions. Benchmarked against linear random projection, such nonlinear mapping embedded with rich physical computational operations shows improved performance across a large collection of machine learning tasks in image classification, regression, and graph classification with varying complexity. Demonstrating up to 27,648 input and 3,500 nonlinear output nodes, the combination of optical nonlinearity and random scattering serves as a scalable computing engine for diverse applications.