# Ensemble learning of diffractive optical networks

arXiv: https://arxiv.org/abs/2009.06869 · HTML: https://mlsanity.com/paper/2009.06869/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2020.

## Built on by (most cited first, 19 of 19)

- [All-Optical Synthesis of an Arbitrary Linear Transformation Using Diffractive Surfaces](https://mlsanity.com/paper/2108.09833/) (2021)
- [Spatially Varying Nanophotonic Neural Networks](https://mlsanity.com/paper/2308.03407/) (2023)
- [Polarization Multiplexed Diffractive Computing: All-Optical Implementation of a Group of Linear Transformations Through a Polarization-Encoded Diffractive Network](https://mlsanity.com/paper/2203.13482/) (2022)
- [All-optical graph representation learning using integrated diffractive photonic computing units](https://mlsanity.com/paper/2204.10978/) (2022)
- [Classification and reconstruction of spatially overlapping phase images using diffractive optical networks](https://mlsanity.com/paper/2108.07977/) (2021)
- [All-optical image classification through unknown random diffusers using a single-pixel diffractive network](https://mlsanity.com/paper/2208.03968/) (2022)
- [Physics-aware Differentiable Discrete Codesign for Diffractive Optical Neural Networks](https://mlsanity.com/paper/2209.14252/) (2022)
- [Analysis of Diffractive Neural Networks for Seeing Through Random Diffusers](https://mlsanity.com/paper/2205.00428/) (2022)
- [Time-lapse image classification using a diffractive neural network](https://mlsanity.com/paper/2208.10802/) (2022)
- [Rubik's Optical Neural Networks: Multi-task Learning with Physics-aware Rotation Architecture](https://mlsanity.com/paper/2304.12985/) (2023)
- [Pyramid diffractive optical networks for unidirectional image magnification and demagnification](https://mlsanity.com/paper/2308.15019/) (2023)
- [EEG Opto-processor: epileptic seizure detection using diffractive photonic computing units](https://mlsanity.com/paper/2301.10167/) (2022)
- [Multiplexed all-optical permutation operations using a reconfigurable diffractive optical network](https://mlsanity.com/paper/2402.02397/) (2024)
- [High Throughput Multi-Channel Parallelized Diffraction Convolutional Neural Network Accelerator](https://mlsanity.com/paper/2112.12297/) (2021)
- [Misaligned orientations of 4f optical neural network for image classification accuracy on various datasets](https://mlsanity.com/paper/2210.08004/) (2022)
- [Scientific Computing with Diffractive Optical Neural Networks](https://mlsanity.com/paper/2302.10905/) (2023)
- [1-bit Quantized On-chip Hybrid Diffraction Neural Network Enabled by Authentic All-optical Fully-connected Architecture](https://mlsanity.com/paper/2404.07443/) (2024)
- [Illumination Angular Spectrum Encoding for Controlling the Functionality of Diffractive Networks](https://mlsanity.com/paper/2601.04825/) (2026)
- [Automated HER2 scoring with uncertainty quantification using lensfree holography and deep learning](https://mlsanity.com/paper/2601.18219/) (2026)

## Abstract (arXiv)

A plethora of research advances have emerged in the fields of optics and photonics that benefit from harnessing the power of machine learning. Specifically, there has been a revival of interest in optical computing hardware, due to its potential advantages for machine learning tasks in terms of parallelization, power efficiency and computation speed. Diffractive Deep Neural Networks (D2NNs) form such an optical computing framework, which benefits from deep learning-based design of successive diffractive layers to all-optically process information as the input light diffracts through these passive layers. D2NNs have demonstrated success in various tasks, including e.g., object classification, spectral-encoding of information, optical pulse shaping and imaging, among others. Here, we significantly improve the inference performance of diffractive optical networks using feature engineering and ensemble learning. After independently training a total of 1252 D2NNs that were diversely engineered with a variety of passive input filters, we applied a pruning algorithm to select an optimized ensemble of D2NNs that collectively improve their image classification accuracy. Through this pruning, we numerically demonstrated that ensembles of N=14 and N=30 D2NNs achieve blind testing accuracies of 61.14% and 62.13%, respectively, on the classification of CIFAR-10 test images, providing an inference improvement of >16% compared to the average performance of the individual D2NNs within each ensemble. These results constitute the highest inference accuracies achieved to date by any diffractive optical neural network design on the same dataset and might provide a significant leapfrog to extend the application space of diffractive optical image classification and machine vision systems.