Photonic Neural Network Fabricated on Thin Film Lithium Niobate for High-Fidelity and Power-Efficient Matrix Computation

TL;DR

This paper introduces the first electro-optic tunable photonic neural network on thin film lithium niobate, demonstrating high fidelity, speed, and power efficiency for AI tasks, paving the way for scalable energy-efficient photonic computing.

Contribution

It presents the first implementation of an EO tunable PNN on TFLN, showcasing ultra-high fidelity and power efficiency for AI applications.

Findings

Achieved high computation speed and low optical loss.

Demonstrated successful classification in multiple AI benchmarks.

Showcased energy-efficient operation suitable for scalable photonic AI systems.

Abstract

Photonic neural networks (PNNs) have emerged as a promising platform to address the energy consumption issue that comes with the advancement of artificial intelligence technology, and thin film lithium niobate (TFLN) offers an attractive solution as a material platform mainly for its combined characteristics of low optical loss and large electro-optic (EO) coefficients. Here, we present the first implementation of an EO tunable PNN based on the TFLN platform. Our device features ultra-high fidelity, high computation speed, and exceptional power efficiency. We benchmark the performance of our device with several deep learning missions including in-situ training of Circle and Moons nonlinear datasets classification, Iris flower species recognition, and handwriting digits recognition. Our work paves the way for sustainable up-scaling of high-speed, energy-efficient PNNs.