학술논문
Photonic Convolutional Neural Networks Using Integrated Diffractive Optics
Document Type
Periodical
Author
Source
IEEE Journal of Selected Topics in Quantum Electronics IEEE J. Select. Topics Quantum Electron. Selected Topics in Quantum Electronics, IEEE Journal of. 26(5):1-8 Jan, 2020
Subject
Language
ISSN
1077-260X
1558-4542
1558-4542
Abstract
With recent rapid advances in photonic integrated circuits, it has been demonstrated that programmable photonic chips can be used to implement artificial neural networks. Convolutional neural networks (CNN) are a class of deep learning methods that have been highly successful in applications such as image classification and speech processing. We present an architecture to implement a photonic CNN using the Fourier transform property of integrated star couplers. We show, in computer simulation, high accuracy image classification using the MNIST dataset. We also model component imperfections in photonic CNN and show that the performance degradation can be recovered in a programmable chip. Our proposed architecture provides a large reduction in physical footprint compared to current implementations as it utilizes the natural advantages of optics and hence offers a scalable pathway towards integrated photonic deep learning processors.