Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Heeringa, Tjeerd Jan"'
Classical model reduction techniques project the governing equations onto a linear subspace of the original state space. More recent data-driven techniques use neural networks to enable nonlinear projections. Whilst those often enable stronger compre
Externí odkaz:
http://arxiv.org/abs/2406.12672
This paper presents a method for finding a sparse representation of Barron functions. Specifically, given an $L^2$ function $f$, the inverse scale space flow is used to find a sparse measure $\mu$ minimising the $L^2$ loss between the Barron function
Externí odkaz:
http://arxiv.org/abs/2312.02671
The approximation properties of infinitely wide shallow neural networks heavily depend on the choice of the activation function. To understand this influence, we study embeddings between Barron spaces with different activation functions. These embedd
Externí odkaz:
http://arxiv.org/abs/2305.15839
Reproducing Kernel Hilbert spaces (RKHS) have been a very successful tool in various areas of machine learning. Recently, Barron spaces have been used to prove bounds on the generalisation error for neural networks. Unfortunately, Barron spaces canno
Externí odkaz:
http://arxiv.org/abs/2211.05020
Publikováno v:
In Applied and Computational Harmonic Analysis November 2024 73
