Evolutionary fine-tuning of select weights in pre-quantized convolutional networks improves accuracy over standard rounding for VGG, ResNet, and autoencoder models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Evolutionary fine tuning of quantized convolution-based deep learning models
Evolutionary fine-tuning of select weights in pre-quantized convolutional networks improves accuracy over standard rounding for VGG, ResNet, and autoencoder models.