JournalNature2022
Deep physical neural networks trained with backpropagation
Logan G. Wright, Tatsuhiro Onodera, Martin M. Stein, et al.
Introduces physics-aware training, a hybrid algorithm that applies backpropagation to train deep physical neural networks made from diverse physical substrates like optics, mechanics, and electronics.
731Jan 26, 2022Neural Networks
arXiv