AI Chat AI Image Generator AI Video Text to Speech

Approximation of functions by neural networks

01/29/2019

∙

by Andreas Thom, et al.

∙

∙

We study the approximation of measurable functions on the hypercube by functions arising from affine neural networks. Our main achievement is an approximation of any measurable function f W_n → [-1,1] up to a prescribed precision ε>0 by a bounded number of neurons, depending only on ε and not on the function f or n ∈ N.

page 1

page 2

page 3

page 4

research

∙ 10/23/2018

Some negative results for Neural Networks

We demonstrate some negative results for approximation of functions with...

1 J. M. Almira, et al. ∙

research

∙ 10/04/2021

Universal approximation properties of shallow quadratic neural networks

In this paper we propose a new class of neural network functions which a...

0 Leon Frischauf, et al. ∙

research

∙ 07/08/2020

Approximation with Neural Networks in Variable Lebesgue Spaces

This paper concerns the universal approximation property with neural net...

0 Angela Capel, et al. ∙

research

∙ 06/21/2021

Approximation capabilities of measure-preserving neural networks

Measure-preserving neural networks are well-developed invertible models,...

0 Aiqing Zhu, et al. ∙

research

∙ 10/24/2022

Precision Machine Learning

We explore unique considerations involved in fitting ML models to data w...

0 Eric J. Michaud, et al. ∙

research

∙ 08/14/2021

Optimal Approximation with Sparse Neural Networks and Applications

We use deep sparsely connected neural networks to measure the complexity...

0 Khay Boon Hong, et al. ∙

research

∙ 12/15/2020

Approximation of BV functions by neural networks: A regularity theory approach

In this paper we are concerned with the approximation of functions by si...

0 Benny Avelin, et al. ∙