Batch normalization layers are introduced for neural networks on complex domains with practical implementations for the Siegel disk and tested on radar, graph, and action recognition tasks.
OPTIMIZATION ANDHYPERPARAMETERS Algorithm 2 shows the computation of the product space representation (˜p0, x1,
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
-
Batch Normalization for Neural Networks on Complex Domains
Batch normalization layers are introduced for neural networks on complex domains with practical implementations for the Siegel disk and tested on radar, graph, and action recognition tasks.