AI Chat AI Image Generator AI Video Text to Speech

Deep Neural Network Approximation For Hölder Functions

01/11/2022

∙

by Ahmed Abdeljawad, et al.

∙

∙

In this work, we explore the approximation capability of deep Rectified Quadratic Unit neural networks for Hölder-regular functions, with respect to the uniform norm. We find that theoretical approximation heavily depends on the selected activation function in the neural network.

page 1

page 2

page 3

page 4

research

∙ 06/17/2019

Smooth function approximation by deep neural networks with general activation functions

There has been a growing interest in expressivity of deep neural network...

0 Ilsang Ohn, et al. ∙

research

∙ 12/02/2018

On variation of gradients of deep neural networks

We provide a theoretical explanation of the role of the number of nodes ...

0 Yongdai Kim, et al. ∙

research

∙ 10/28/2019

Growing axons: greedy learning of neural networks with application to function approximation

We propose a new method for learning deep neural network models that is ...

25 Daria Fokina, et al. ∙

research

∙ 04/19/2023

Points of non-linearity of functions generated by random neural networks

We consider functions from the real numbers to the real numbers, output ...

0 David Holmes, et al. ∙

research

∙ 07/23/2020

Nonclosedness of the Set of Neural Networks in Sobolev Space

We examine the closedness of the set of realized neural networks of a fi...

0 Scott Mahan, et al. ∙

research

∙ 12/16/2021

Approximation of functions with one-bit neural networks

This paper examines the approximation capabilities of coarsely quantized...

0 C. Sinan Güntürk, et al. ∙

research

∙ 07/12/2020

Universal Approximation Power of Deep Neural Networks via Nonlinear Control Theory

In this paper, we explain the universal approximation capabilities of de...

0 Paulo Tabuada, et al. ∙