Placing a KAN layer between two linear layers improves spoken language understanding accuracy over linear-only baselines on several speech-intent datasets.
Properties of Chebyshev polynomials
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Ordinary differential equations and boundary value problems arise in many aspects of mathematical physics. Chebyshev differential equation is one special case of the Sturm-Liouville boundary value problem. Generating function, recursive formula, orthogonality, and Parseval's identity are some important properties of Chebyshev polynomials. Compared with a Fourier series, an interpolation function using Chebyshev polynomials is more accurate in approximating polynomial functions. -------- Des \'equations diff\'erentielles ordinaires et des probl\`emes de valeurs limites se posent dans de nombreux aspects de la physique math\'ematique. L'\'equation diff\'erentielle de Chebychev est un cas particulier du probl\`eme de la valeur limite de Sturm-Liouville. La fonction g\'en\'eratrice, la formule r\'ecursive, l'orthogonalit\'e et l'identit\'e de Parseval sont quelques propri\'et\'es importantes du polyn\^ome de Chebyshev. Par rapport \`a une s\'erie de Fourier, une fonction d'interpolation utilisant des polyn\^omes de Chebyshev est plus pr\'ecise dans l'approximation des fonctions polynomiales.
citation-role summary
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
"KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding
Placing a KAN layer between two linear layers improves spoken language understanding accuracy over linear-only baselines on several speech-intent datasets.