Highly efficient convolution computing architecture based on silicon photonic Fano resonance devices
DOI:
Author:
Affiliation:

1.Beijing Information Science & Technology University;2.State grid Zhejiang electric power corporation information & telecommunication branch;3.School of Engineering, RMIT University, Melbourne, Victoria 3000 Australia

Clc Number:

Fund Project:

State grid Zhejiang electric power corporation information & telecommunication branch (No.B311XT21004G)

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    Convolutional neural networks require a lot of multiplication and addition operations completed by traditional electrical multipliers, leading to high power consumption and limited speed. Here, a silicon waveguide-based wavelength division multiplexing architecture for convolution neural network is optimized with high energy efficiency Fano resonator. Coupling of T-waveguide and Micro-ring resonator generate Fano resonance with small half-width, which can significantly reduce the modulator power consumption. National Grid's insulator dataset is used to test Fano resonance modulator-based convolutional neural networks. The results show that accuracy for insulator defect recognition reaches 99.27% with much lower power consumption. Obviously, Our opti-mized photonic integration architecture for convolutional neural networks has broad potential for the artificial intelligence hardware platform.

    Reference
    Related
    Cited by
Get Citation
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:March 16,2023
  • Revised:March 23,2023
  • Adopted:April 06,2023
  • Online:
  • Published: