Cargando…
Analytic Function Approximation by Path-Norm-Regularized Deep Neural Networks
We show that neural networks with an absolute value activation function and with network path norm, network sizes and network weights having logarithmic dependence on [Formula: see text] can [Formula: see text]-approximate functions that are analytic on certain regions of [Formula: see text].
Autor principal: | Beknazaryan, Aleksandr |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9407526/ https://www.ncbi.nlm.nih.gov/pubmed/36010799 http://dx.doi.org/10.3390/e24081136 |
Ejemplares similares
-
Nuclear Norm Regularized Deep Neural Network for EEG-Based Emotion Recognition
por: Liang, Shuang, et al.
Publicado: (2022) -
A Frobenius Norm Regularization Method for Convolutional Kernel Tensors in Neural Networks
por: Guo, Pei-Chang
Publicado: (2022) -
Smooth Function Approximation by Deep Neural Networks with General Activation Functions
por: Ohn, Ilsang, et al.
Publicado: (2019) -
Regularity and approximability of electronic wave functions
por: Yserentant, Harry
Publicado: (2010) -
Quaternionic approximation: with application to slice regular functions
por: Gal, Sorin G, et al.
Publicado: (2019)