A toric-geometry framework for ReLU networks yields a necessary and sufficient intersection-number criterion for exact realizability by unbiased shallow ReLU networks.
Activation degree thresholds and expressiveness of polynomial neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.AG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Toric geometry of ReLU neural networks
A toric-geometry framework for ReLU networks yields a necessary and sufficient intersection-number criterion for exact realizability by unbiased shallow ReLU networks.