Optical machine learning with incoherent light and a single-pixel detector

Abstract

An optical diffractive neural network (DNN) can be implemented with a cascaded phase mask architecture. Like an optical computer, the system can perform machine learning tasks such as number digit recognition in an all-optical manner. However, the system can only work under coherent light illumination and the precision requirement in practical experiments is quite high. This paper proposes an optical machine learning framework based on single-pixel imaging (MLSPI). The MLSPI system can perform the same linear pattern recognition task as DNN. Furthermore, it can work under incoherent lighting conditions, has lower experimental complexity and can be easily programmable.

References in corpus (6)

• All-Optical Machine Learning Using Diffractive Deep Neural Networks
• Efficient and mode selective spatial mode multiplexer based on Multi-Plane Light Conversion
• Experimental comparison of single-pixel imaging algorithms
• Review on Optical Image Hiding and Watermarking Techniques
• Single-pixel imaging with sampling distributed over simplex vertices
• Compressive phase-only filtering at extreme compression rates

Cited by in corpus (14)

• Visual cryptography in single-pixel imaging
• Image-free real-time classification of fast moving objects using 'learned' spatial light modulation and a single-pixel detector
• Does deep learning always outperform simple linear regression in optical imaging?
• Multiple-image encryption and hiding with an optical diffractive neural network
• A Two-step-training Deep Learning Framework for Real-time Computational Imaging without Physics Priors
• Non-imaging single-pixel sensing with optimized binary modulation
• Scalability of all-optical neural networks based on spatial light modulators
• Classification and reconstruction of spatially overlapping phase images using diffractive optical networks
• Robust and Efficient Single-Pixel Image Classificationwith Nonlinear Optics
• Single-Pixel Pattern Recognition with Coherent Nonlinear Optics
• Gigahertz-rate random speckle projection for high-speed single-pixel image classification
• Single-pixel diffuser camera
• Classification and reconstruction for single-pixel imaging with classical and quantum neural networks
• High speed and reconfigurable optronic neural network with digital nonlinear activation