The c-TTv2 analog algorithm fine-tuned a Swin-ViT transformer on CIFAR-100 subsets in simulation, landed within about 2% of digital transfer learning, and tolerated up to 10-15% weight-transfer noise.
Large language models in finance: A survey,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Assessing the Performance of Analog Training for Transfer Learning
The c-TTv2 analog algorithm fine-tuned a Swin-ViT transformer on CIFAR-100 subsets in simulation, landed within about 2% of digital transfer learning, and tolerated up to 10-15% weight-transfer noise.