Training neural networks with end-to-end optical backpropagation

no code implementations • 9 Aug 2023 • James Spall, Xianxin Guo, A. I. Lvovsky

Optics is an exciting route for the next generation of computing hardware for machine learning, promising several orders of magnitude enhancement in both computational speed and energy efficiency.

Hybrid training of optical neural networks

no code implementations • 20 Mar 2022 • James Spall, Xianxin Guo, A. I. Lvovsky

Optical neural networks are emerging as a promising type of machine learning hardware capable of energy-efficient, parallel computation.

Backpropagation through nonlinear units for all-optical training of neural networks

1 code implementation • 23 Dec 2019 • Xianxin Guo, Thomas D. Barrett, Zhiming M. Wang, A. I. Lvovsky

Backpropagation through nonlinear neurons is an outstanding challenge to the field of optical neural networks and the major conceptual barrier to all-optical training schemes.

Emerging Technologies Signal Processing Optics