CoFrNet represents functions as stacked continued fractions with linear layers and reciprocal activation, but the universal approximation proof applies to a more general function class than the architecture used in experiments.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
CoFrNets: Interpretable Neural Architecture Inspired by Continued Fractions
CoFrNet represents functions as stacked continued fractions with linear layers and reciprocal activation, but the universal approximation proof applies to a more general function class than the architecture used in experiments.