ZeNNs, which replace the equal-weight average of MLP neurons with an index-weighted sum of frequency-scaled neurons, provably converge pointwise, retain non-Gaussian limits, and learn high-frequency features in low-dimensional tasks.
Mathematical aspects of deep learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A ZeNN architecture to avoid the Gaussian trap
ZeNNs, which replace the equal-weight average of MLP neurons with an index-weighted sum of frequency-scaled neurons, provably converge pointwise, retain non-Gaussian limits, and learn high-frequency features in low-dimensional tasks.