Loading...

High-Speed multi-layer convolutional neural network based on free-space optics

Sadeghzadeh, H ; Sharif University of Technology | 2022

107 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/JPHOT.2022.3180675
  3. Publisher: Institute of Electrical and Electronics Engineers Inc , 2022
  4. Abstract:
  5. Convolutional neural networks (CNNs) are at the heart of several machine learning applications, while they suffer from computational complexity due to their large number of parameters and operations. Recently, all-optical implementation of the CNNs has achieved many attentions, however, the recently proposed optical architectures for CNNs cannot fully utilize the tremendous capabilities of optical processing, due to the required electro-optical conversions in-between successive layers. To implement an all-optical multi-layer CNN, it is essential to optically implement all required operations, namely convolution, summation of channels' output for each convolutional kernel feeding the nonlinear unit, nonlinear activation function, and finally, pooling operations. Considering the lack of multi-layer photonic CNN implementation, in this paper, we explore a fully-optical design for implementing successive convolutional layers in an optical CNN. As a proof of concept, and without loss of generality, we considered two successive optical layers in the proposed network, named as 2L-OPCNN, for comparative studies against electrical counterpart and single optical layer CNN. Our simulation results confirm nearly the same accuracies for classifying images of Kaggle Cats and Dogs challenge, CIFAR-10, and MNIST datasets, compared to the electrical counterpart, as well as improved accuracies compared to single optical layer CNN. © 2009-2012 IEEE
  6. Keywords:
  7. Deep convolutional neural network ; Optical correlator ; Classification (of information) ; Deep neural networks ; Image classification ; Image enhancement ; Multilayer neural networks ; Network layers ; Nonlinear optics ; Optical data processing ; Optical design ; Optical fiber communication ; Optical fibers ; All optical ; All-optical neural network ; Biomedical optical imaging ; High performance neural network ; Images classification ; Neural-networks ; Optical correlators ; Optical fiber networks ; Optical imaging ; Optical network units ; Optical neural networks ; Performance ; Convolution
  8. Source: IEEE Photonics Journal ; Volume 14, Issue 4 , 2022 ; 19430655 (ISSN)
  9. URL: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9790077