CDF normalization to quantiles improves MNIST test accuracy and training speed of Legendre-KAN compared with min-max scaling.
Legendre-kan: High accuracy ka network based on legendre polynomials
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
extension 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
extension 1polarities
extend 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.