All-Optical Machine Learning Using Diffractive Deep Neural Networks

TL;DR

This paper presents a novel all-optical deep neural network architecture, D2NN, that uses passive diffractive layers to perform complex functions like image classification and lens functions at the speed of light, enabling rapid optical processing.

Contribution

The paper introduces the D2NN framework, demonstrating its ability to implement neural network functions optically using 3D-printed diffractive layers, a significant advancement in all-optical computing.

Findings

Successfully demonstrated handwritten digit classification using D2NN

Implemented optical lens functions at terahertz spectrum with D2NN

Achieved real-time, all-optical processing at the speed of light

Abstract

We introduce an all-optical Diffractive Deep Neural Network (D2NN) architecture that can learn to implement various functions after deep learning-based design of passive diffractive layers that work collectively. We experimentally demonstrated the success of this framework by creating 3D-printed D2NNs that learned to implement handwritten digit classification and the function of an imaging lens at terahertz spectrum. With the existing plethora of 3D-printing and other lithographic fabrication methods as well as spatial-light-modulators, this all-optical deep learning framework can perform, at the speed of light, various complex functions that computer-based neural networks can implement, and will find applications in all-optical image analysis, feature detection and object classification, also enabling new camera designs and optical components that can learn to perform unique tasks using D2NNs.