Design of diffractive neural networks solving different classification problems at different wavelengths

TL;DR

This paper presents a gradient-based method for designing diffractive neural networks that can classify different datasets at multiple wavelengths, demonstrating high performance through simulations.

Contribution

It introduces a novel gradient optimization approach for designing multi-wavelength diffractive neural networks for various classification tasks.

Findings

Successful classification of MNIST, Fashion MNIST, and EMNIST datasets at different wavelengths.

Explicit derivative expressions enable efficient gradient-based design.

Simulations show high accuracy and effectiveness of the proposed method.

Abstract

We consider the problem of designing a diffractive neural network (DNN) consisting of a set of sequentially placed phase diffractive optical elements (DOEs) and intended for the optical solution of several given classification problems at different operating wavelengths, so that each classification problem is solved at the corresponding wavelength. The problem of calculating the DNN is formulated as the problem of minimizing a functional that depends on the functions of the diffractive microrelief height of the DOEs constituting the DNN and represents the error in solving the given classification problems at the operating wavelengths. We obtain explicit and compact expressions for the derivatives of this functional and, using them, formulate a gradient method for the DNN calculation. Using this method, we design DNNs for solving the following three classification problems at three different wavelengths: the problem of classifying handwritten digits from the MNIST database, the problem of classifying fashion products from the Fashion MNIST database, and the problem of classifying ten handwritten letters from the EMNIST database. The presented simulation results of the designed DNNs demonstrate high performance of the proposed method.