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...
Главные авторы: | Spall, J, Guo, X, Lvovsky, A |
---|---|
Формат: | Journal article |
Язык: | English |
Опубликовано: |
Society of Photo-Optical Instrumentation Engineers
2025
|
Схожие документы
-
Training neural networks with end-to-end optical backpropagation
по: Spall, J
Опубликовано: (2024) -
Hybrid training of optical neural networks
по: Spall, J, и др.
Опубликовано: (2022) -
Backpropagation through nonlinear units for the all-optical training of neural networks
по: Guo, X, и др.
Опубликовано: (2021) -
End-to-End Training of Deep Neural Networks in the Fourier Domain
по: András Fülöp, и др.
Опубликовано: (2022-06-01) -
Training Deep Spiking Neural Networks using Backpropagation
по: Jun Haeng Lee, и др.
Опубликовано: (2016-11-01)