Optical convolutional neural network with atomic nonlinearity

Yang, Mingwei; Robertson, Elizabeth J.; Rodríguez, Luisa Esguerra; Busch, Kurt; Wolters, Janik

doi:10.1364/oe.490070

Cited by 4 publications

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to linear optics, nonlinear optical techniques are gaining significant applications in various fields [19][20][21][22][23][24]. Nonlinear activation functions, which can be directly applied to optical signals without the need for conversion to electronics, offer several advantages.…”

mentioning

confidence: 99%

Single-pixel Image Reconstruction Using Coherent Nonlinear Optics

Thomas¹,

Kumar²,

Huang³

2023

Preprint

View full text Add to dashboard Cite

We propose and experimentally demonstrate a novel hybrid optoelectronic system that utilizes mode-selective frequency upconversion, single-pixel detection, and a deep neural network to achieve the reliable reconstruction of 2D images from a noise-contaminated database of handwritten digits. Our system is designed to maximize the multi-scale structural similarity index measure (MS-SSIM) and minimize the mean absolute error (MAE) during the training process. Through extensive evaluation, we have observed that the reconstructed images exhibit high-quality results, with a peak signal-to-noise ratio (PSNR) reaching approximately 20 dB and a structural similarity index measure (SSIM) of around 0.85. These impressive metrics demonstrate the effectiveness and fidelity of our image reconstruction technique. The versatility of our approach allows its application in various fields, including Lidar, compressive imaging, volumetric reconstruction, and so on.

show abstract

mentioning

confidence: 99%

Single-pixel Image Reconstruction Using Coherent Nonlinear Optics

Thomas¹,

Kumar²,

Huang³

2023

Preprint

View full text Add to dashboard Cite

show abstract

AI meets physics: a comprehensive survey

Jiao,

Song,

You

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

Quantitative comparison of the computational complexity of optical, digital and hybrid neural network architectures for image classification tasks

Chen,

Schoenhardt,

et al. 2023

Opt. Express

View full text Add to dashboard Cite

By implementing neuromorphic paradigms in processing visual information, machine learning became crucial in an ever-increasing number of applications of our everyday lives, ever more performing but also computationally demanding. While a pre-processing of the information passively in the optical domain, before optical-electronic conversion, can reduce the computational requirements for a machine learning task, a comprehensive analysis of computational requirements for hybrid optical-digital neural networks is thus far missing. In this work we critically compare and analyze the performance of different optical, digital and hybrid neural network architectures with respect to their classification accuracy and computational requirements for analog classification tasks of different complexity. We show that certain hybrid architectures exhibit a reduction of computational requirements of a factor >10 while maintaining their performance. This may inspire a new generation of co-designed optical-digital neural network architectures, aimed for applications that require low power consumption like remote sensing devices.

show abstract

Optical convolutional neural network with atomic nonlinearity

Cited by 4 publications

References 30 publications

Single-pixel Image Reconstruction Using Coherent Nonlinear Optics

Single-pixel Image Reconstruction Using Coherent Nonlinear Optics

AI meets physics: a comprehensive survey

Quantitative comparison of the computational complexity of optical, digital and hybrid neural network architectures for image classification tasks

Contact Info

Product

Resources

About