Sharpness-aware training makes physical neural networks robust to modeling error, fabrication variance, and post-deployment perturbations, enabling accurate offline and transferable online training.
Nature 588(7836), 39–47 (2020)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.optics 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Perfecting Imperfect Physical Neural Networks with Transferable Robustness using Sharpness-Aware Training
Sharpness-aware training makes physical neural networks robust to modeling error, fabrication variance, and post-deployment perturbations, enabling accurate offline and transferable online training.