Training neural networks with end-to-end optical backpropagation
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. However, reaching the full capacity of an optical neural network necessitates the computing be implemen...
Main Authors: | Spall, J, Guo, X, Lvovsky, A |
---|---|
Formato: | Journal article |
Idioma: | English |
Publicado em: |
Society of Photo-Optical Instrumentation Engineers
2025
|
Registos relacionados
-
Training neural networks with end-to-end optical backpropagation
Por: Spall, J
Publicado em: (2024) -
Hybrid training of optical neural networks
Por: Spall, J, et al.
Publicado em: (2022) -
Backpropagation through nonlinear units for the all-optical training of neural networks
Por: Guo, X, et al.
Publicado em: (2021) -
End-to-End Training of Deep Neural Networks in the Fourier Domain
Por: András Fülöp, et al.
Publicado em: (2022-06-01) -
Training Deep Spiking Neural Networks using Backpropagation
Por: Jun Haeng Lee, et al.
Publicado em: (2016-11-01)