Scientific Computing with Diffractive Optical Neural Networks

TL;DR

This paper demonstrates the use of diffractive optical neural networks (DONNs) for diverse scientific computing tasks, expanding their application beyond simple image classification to complex ML problems in materials science, quantum physics, and control systems.

Contribution

The authors introduce a universal feature engineering method for processing various data types in DONNs and experimentally validate their system for multiple scientific computing applications.

Findings

Successful deployment of DONNs for quantum material synthesis

Accurate property prediction of nanomaterials and drugs

Effective stabilization of an inverted pendulum using reinforcement learning

Abstract

Diffractive optical neural networks (DONNs) have been emerging as a high-throughput and energy-efficient hardware platform to perform all-optical machine learning (ML) in machine vision systems. However, the current demonstrated applications of DONNs are largely straightforward image classification tasks, which undermines the prospect of developing and utilizing such hardware for other ML applications. Here, we numerically and experimentally demonstrate the deployment of an all-optical reconfigurable DONNs system for scientific computing, including guiding two-dimensional quantum material synthesis, predicting the properties of nanomaterials and small molecular cancer drugs, predicting the device response of nanopatterned integrated photonic power splitters, and the dynamic stabilization of an inverted pendulum with reinforcement learning. Despite a large variety of input data structures, we develop a universal feature engineering approach to convert categorical input features to the images that can be processed in the DONNs system. Our results open up new opportunities of employing DONNs systems for a broad range of ML applications.