A framework using measured noise proxies, chance-constrained training, and noise-aware LayerNorm enables Vision Transformers to achieve near-clean accuracy on noisy microring-resonator photonic arrays without in-situ learning or added optical operations.
Memory technologies for crossbar array design: a comparative evaluation of their impact on dnn accuracy.IEEE Transactions on Circuits and Systems I: Regular Papers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.ET 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Light-Bound Transformers: Hardware-Anchored Robustness for Silicon-Photonic Computer Vision Systems
A framework using measured noise proxies, chance-constrained training, and noise-aware LayerNorm enables Vision Transformers to achieve near-clean accuracy on noisy microring-resonator photonic arrays without in-situ learning or added optical operations.