Výsledky vyhledávání - "Braun, Alina"

Dissertation/ Thesis

In Theory and Practice - On the Rate of Convergence of Implementable Neural Network Regression Estimates

Autor: Braun, Alina

In theory, recent results in nonparametric regression show that neural network estimates are able to achieve good rates of convergence provided suitable assumptions on the structure of the regression function are imposed. However, these theoretical a

Externí odkaz: https://tuprints.ulb.tu-darmstadt.de/19052/1/Dissertation_BraunAlina_genehmigt.pdf

Zobrazit plný text záznamu

Report

Convergence rates for shallow neural networks learned by gradient descent

Autor: Braun, Alina, Kohler, Michael, Langer, Sophie, Walk, Harro

In this paper we analyze the $L_2$ error of neural network regression estimates with one hidden layer. Under the assumption that the Fourier transform of the regression function decays suitably fast, we show that an estimate, where all initial weight

Externí odkaz: http://arxiv.org/abs/2107.09550

Zobrazit plný text záznamu

Report

Analysis of the rate of convergence of neural network regression estimates which are easy to implement

Autor: Braun, Alina, Kohler, Michael, Krzyzak, Adam

Recent results in nonparametric regression show that for deep learning, i.e., for neural network estimates with many hidden layers, we are able to achieve good rates of convergence even in case of high-dimensional predictor variables, provided suitab

Externí odkaz: http://arxiv.org/abs/1912.05436

Zobrazit plný text záznamu

Report

On the rate of convergence of a neural network regression estimate learned by gradient descent

Autor: Braun, Alina, Kohler, Michael, Walk, Harro

Nonparametric regression with random design is considered. Estimates are defined by minimzing a penalized empirical $L_2$ risk over a suitably chosen class of neural networks with one hidden layer via gradient descent. Here, the gradient descent proc

Externí odkaz: http://arxiv.org/abs/1912.03921

Zobrazit plný text záznamu