Training-time batch normalization increases expected local affine-region density in ReLU and piecewise-affine networks by acting as a batch-conditional recentering mechanism on switching hyperplanes.
Journal of Computational Mathematics , volume =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3roles
background 3polarities
background 3representative citing papers
AffineLens enumerates the maximal continuous piecewise-affine regions induced by neural networks with batch-norm, pooling, residuals and convolutions inside a bounded input polytope and supplies visualizations and region-count metrics.
A pre-activation regularizer seeds more affine regions near data in piecewise affine networks, increasing local region count and improving early training performance.
citing papers explorer
-
Training-Time Batch Normalization Reshapes Local Partition Geometry in Piecewise-Affine Networks
Training-time batch normalization increases expected local affine-region density in ReLU and piecewise-affine networks by acting as a batch-conditional recentering mechanism on switching hyperplanes.
-
AffineLens: Capturing the Continuous Piecewise Affine Functions of Neural Networks
AffineLens enumerates the maximal continuous piecewise-affine regions induced by neural networks with batch-norm, pooling, residuals and convolutions inside a bounded input polytope and supplies visualizations and region-count metrics.
-
Region Seeding via Pre-Activation Regularization: A Geometric View of Piecewise Affine Neural Networks
A pre-activation regularizer seeds more affine regions near data in piecewise affine networks, increasing local region count and improving early training performance.