Photonic Convolutional Neural Networks Using Integrated Diffractive Optics
| Autor: | Ching Eng Png, Soon Thor Lim, Jun Rong Ong, Thomas Y. L. Ang, Chin Chun Ooi |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Signal Processing (eess.SP)
Artificial neural network business.industry Computer science Deep learning Computer Science::Neural and Evolutionary Computation Photonic integrated circuit FOS: Physical sciences Convolutional neural network Atomic and Molecular Physics and Optics Computer Science::Hardware Architecture Neuromorphic engineering Scalability FOS: Electrical engineering electronic engineering information engineering Electronic engineering Artificial intelligence Electrical Engineering and Systems Science - Signal Processing Electrical and Electronic Engineering Photonics business MNIST database Physics - Optics Optics (physics.optics) |
| Zdroj: | IEEE Journal of Selected Topics in Quantum Electronics. 26:1-8 |
| ISSN: | 1558-4542 1077-260X |
| DOI: | 10.1109/jstqe.2020.2982990 |
| Popis: | 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. Comment: 9 pages, 6 figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|