A Broad-Spectrum Diffractive Network via Ensemble Learning

TL;DR

This paper introduces a broad-spectrum diffractive deep neural network that leverages multi-wavelength input channels and ensemble learning to achieve high-accuracy object classification insensitive to wavelength variations.

Contribution

It presents a novel BS-D2NN framework combining multi-channel optical modulation and ensemble learning for wavelength-insensitive classification.

Findings

Achieves high-accuracy object classification across multiple wavelengths.

Utilizes optical sum and hybrid maxout operations for improved learning.

Demonstrates wavelength-insensitive performance through deep learning training.

Abstract

We proposed a broad-spectrum diffractive deep neural network (BS-D2NN) framework, which incorporates multi-wavelength channels of input lightfields and performs a parallel phase-only modulation utilizing a layered passive mask architecture. A complementary multi-channel base learner cluster is formed in a homogeneous ensemble framework based on the diffractive dispersion during lightwave modulation. In addition, both the optical Sum operation and the Hybrid (optical-electronic) Maxout operation are performed for motivating the BS-D2NN to learn and construct a mapping between input lightfields and truth labels under heterochromatic ambient lighting. The BS-D2NN can be trained using deep learning algorithms so as to perform a kind of wavelength-insensitive high-accuracy object classification.