Silicon photonic architecture for training deep neural networks with direct feedback alignment

Matthew J. Filipovich, Zhimu Guo, Mohammed Al-Qadasi, Bicky A. Marquez, Hugh D. Morison, Volker J. Sorger, Paul R. Prucnal, Sudip Shekhar, Bhavin J. Shastri

Research output: Contribution to journalArticlepeer-review

16 Scopus citations


There has been growing interest in using photonic processors for performing neural network inference operations; however, these networks are currently trained using standard digital electronics. Here, we propose on-chip training of neural networks enabled by a CMOS-compatible silicon photonic architecture to harness the potential for massively parallel, efficient, and fast data operations. Our scheme employs the direct feedback alignment training algorithm, which trains neural networks using error feedback rather than error backpropagation, and can operate at speeds of trillions of multiply–accumulate (MAC) operations per second while consuming less than one picojoule per MAC operation. The photonic architecture exploits parallelized matrix–vector multiplications using arrays of microring resonators for processing multi-channel analog signals along single waveguide buses to calculate the gradient vector for each neural network layer in situ. We also experimentally demonstrate training deep neural networks with the MNIST dataset using on-chip MAC operation results. Our approach for efficient, ultra-fast neural network training showcases photonics as a promising platform for executing artificial intelligence applications.

Original languageEnglish (US)
Pages (from-to)1323-1332
Number of pages10
Issue number12
StatePublished - Dec 20 2022

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics


Dive into the research topics of 'Silicon photonic architecture for training deep neural networks with direct feedback alignment'. Together they form a unique fingerprint.

Cite this