Ensemble learning of diffractive optical networks

Abstract

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.

22 Pages, 4 Figures, 1 Table

References in corpus (16)

• Neural Machine Translation by Jointly Learning to Align and Translate
• Deep Learning with Coherent Nanophotonic Circuits
• All-Optical Machine Learning Using Diffractive Deep Neural Networks
• Neuromorphic Silicon Photonic Networks
• Deep Learning Microscopy
• Training of photonic neural networks through in situ backpropagation
• Reinforcement Learning in a large scale photonic Recurrent Neural Network
• Wave Physics as an Analog Recurrent Neural Network
• Extended depth-of-field in holographic image reconstruction using deep learning based auto-focusing and phase-recovery
• Design of Task-Specific Optical Systems Using Broadband Diffractive Neural Networks
• Analysis of Diffractive Optical Neural Networks and Their Integration with Electronic Neural Networks
• Terahertz Pulse Shaping Using Diffractive Surfaces
• Class-specific Differential Detection in Diffractive Optical Neural Networks Improves Inference Accuracy
• All-Optical Information Processing Capacity of Diffractive Surfaces
• Misalignment Resilient Diffractive Optical Networks
• Photonic convolutional neural networks using integrated diffractive optics

Cited by in corpus (20)

• Computational Imaging Without a Computer: Seeing Through Random Diffusers at the Speed of Light
• Polarization Multiplexed Diffractive Computing: All-Optical Implementation of a Group of Linear Transformations Through a Polarization-Encoded Diffractive Network
• Intelligent Meta-Imagers: From Compressed to Learned Sensing
• Massively Parallel Universal Linear Transformations using a Wavelength-Multiplexed Diffractive Optical Network
• Scale-, shift- and rotation-invariant diffractive optical networks
• All-optical image classification through unknown random diffusers using a single-pixel diffractive network
• Universal Linear Intensity Transformations Using Spatially-Incoherent Diffractive Processors
• Data class-specific all-optical transformations and encryption
• Universal Polarization Transformations: Spatial programming of polarization scattering matrices using a deep learning-designed diffractive polarization transformer
• Classification and reconstruction of spatially overlapping phase images using diffractive optical networks
• Simultaneously sorting vector vortex beams of 120 modes
• Ultrahigh-fidelity spatial mode quantum gates in high-dimensional space by diffractive deep neural networks
• Pyramid diffractive optical networks for unidirectional image magnification and demagnification
• Complex-valued universal linear transformations and image encryption using spatially incoherent diffractive networks
• Time-lapse image classification using a diffractive neural network
• Multiplexed all-optical permutation operations using a reconfigurable diffractive optical network
• Analysis of Diffractive Neural Networks for Seeing Through Random Diffusers
• Polarization and Orbital Angular Momentum Encoded Quantum Toffoli Gate Enabled by Diffractive Neural Networks
• Computer-free, all-optical reconstruction of holograms using diffractive networks
• All-Optical Synthesis of an Arbitrary Linear Transformation Using Diffractive Surfaces