For ReLU networks with width at least two in input and hidden layers, an open set of parameters is identifiable, implying functional dimension equals parameter count minus hidden neurons.
Constraining the outputs of ReLU neural networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Lightning self-attention coefficients are coordinates on an algebraic variety obeying Chow-type, low-rank, Veronese-type, and Sylvester-resultant invariants.
citing papers explorer
-
Most ReLU Networks Admit Identifiable Parameters
For ReLU networks with width at least two in input and hidden layers, an open set of parameters is identifiable, implying functional dimension equals parameter count minus hidden neurons.
-
Algebraic Invariants of Lightning Self-Attention
Lightning self-attention coefficients are coordinates on an algebraic variety obeying Chow-type, low-rank, Veronese-type, and Sylvester-resultant invariants.