Non-volatile Reconfigurable Digital Optical Diffractive Neural Network Based on Phase Change Material

TL;DR

This paper introduces a reconfigurable, non-volatile digital optical neural network utilizing phase-change materials, achieving high accuracy in image recognition with low power and high speed.

Contribution

It presents a novel all-optical diffractive neural network with phase-change materials enabling reconfigurability and non-volatility, advancing optical neural network technology.

Findings

Achieved 94.46% accuracy in handwritten digit recognition.

Demonstrated robustness through full-vector simulations.

Showcased feasibility of reconfigurable optical neural networks.

Abstract

Optical diffractive neural networks have triggered extensive research with their low power consumption and high speed in image processing. In this work, we propose a reconfigurable digital all-optical diffractive neural network (R-ODNN) structure. The optical neurons are built with Sb2Se3 phase-change material, making our network reconfigurable, digital, and non-volatile. Using three digital diffractive layers with 14,400 neurons on each and 10 photodetectors connected to a resistor network, our model achieves 94.46% accuracy for handwritten digit recognition. We also performed full-vector simulations and discussed the impact of errors to demonstrate the feasibility and robustness of the R-ODNN.