ASR applies per-channel variance-matching corrections stabilized by data-driven shrinkage to recover accuracy in highly sparse convolutional networks without retraining.
Batch normalization: Accelerating deep network training by reducing internal covariate shift
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Every fixed finite feedforward neural network definable in an o-minimal structure has finite sample complexity in the agnostic PAC setting.
citing papers explorer
-
Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks
ASR applies per-channel variance-matching corrections stabilized by data-driven shrinkage to recover accuracy in highly sparse convolutional networks without retraining.
-
Every Feedforward Neural Network Definable in an o-Minimal Structure Has Finite Sample Complexity
Every fixed finite feedforward neural network definable in an o-minimal structure has finite sample complexity in the agnostic PAC setting.