HEQ sets quantization step sizes from weight quantiles, achieving competitive CIFAR-10 accuracy and enabling logic-gated residual networks on STL-10.
Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1,
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
-
Histogram-Equalized Quantization for logic-gated Residual Neural Networks
HEQ sets quantization step sizes from weight quantiles, achieving competitive CIFAR-10 accuracy and enabling logic-gated residual networks on STL-10.