CDF normalization to quantiles improves MNIST test accuracy and training speed of Legendre-KAN compared with min-max scaling.
The kolmogorov–arnold representation theorem revis- ited,
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
background 1representative citing papers
citing papers explorer
-
Improving KAN with CDF normalization to quantiles
CDF normalization to quantiles improves MNIST test accuracy and training speed of Legendre-KAN compared with min-max scaling.