中文
相关论文

相关论文: On Universal Approximation by Neural Networks with…

200 篇论文

We define a neural network in infinite dimensional spaces for which we can show the universal approximation property. Indeed, we derive approximation results for continuous functions from a Fr\'echet space $\X$ into a Banach space $\Y$. The…

泛函分析 · 数学 2022-05-18 Fred Espen Benth , Nils Detering , Luca Galimberti

The universal approximation theorem is generalised to uniform convergence on the (noncompact) input space $\mathbb{R}^n$. All continuous functions that vanish at infinity can be uniformly approximated by neural networks with one hidden…

机器学习 · 计算机科学 2024-03-05 Teun D. H. van Nuland

The Universal Approximation Theorem posits that neural networks can theoretically possess unlimited approximation capacity with a suitable activation function and a freely chosen or trained set of parameters. However, a more practical…

机器学习 · 计算机科学 2024-09-26 Li Liu , Tengchao Yu , Heng Yong

The universal approximation theorem, in one of its most general versions, says that if we consider only continuous activation functions $\sigma$, then a standard feedforward neural network with one hidden layer is able to approximate any…

机器学习 · 计算机科学 2020-02-18 Kai Fong Ernest Chong

Leveraging the infinite dimensional neural network architecture we proposed in arXiv:2109.13512v4 and which can process inputs from Fr\'echet spaces, and using the universal approximation property shown therein, we now largely extend the…

泛函分析 · 数学 2024-06-14 Luca Galimberti

In this paper, we explain the universal approximation capabilities of deep residual neural networks through geometric nonlinear control. Inspired by recent work establishing links between residual networks and control systems, we provide a…

机器学习 · 计算机科学 2024-02-12 Paulo Tabuada , Bahman Gharesifard

The standard Universal Approximation Theorem for operator neural networks (NNs) holds for arbitrary width and bounded depth. Here, we prove that operator NNs of bounded width and arbitrary depth are universal approximators for continuous…

机器学习 · 计算机科学 2021-09-24 Annan Yu , Chloé Becquey , Diana Halikias , Matthew Esmaili Mallory , Alex Townsend

This paper concerns the universal approximation property with neural networks in variable Lebesgue spaces. We show that, whenever the exponent function of the space is bounded, every function can be approximated with shallow neural networks…

泛函分析 · 数学 2020-07-09 Ángela Capel , Jesús Ocáriz

We study shallow and deep neural networks whose inputs range over a general topological space. The model is built from a prescribed family of continuous feature maps and reduces to multilayer feedforward networks in the Euclidean case. We…

一般拓扑 · 数学 2026-03-24 Vugar Ismailov

Group symmetry is inherent in a wide variety of data distributions. Data processing that preserves symmetry is described as an equivariant map and often effective in achieving high performance. Convolutional neural networks (CNNs) have been…

机器学习 · 统计学 2020-12-29 Wataru Kumagai , Akiyoshi Sannai

We study the universality of complex-valued neural networks with bounded widths and arbitrary depths. Under mild assumptions, we give a full description of those activation functions $\varrho:\mathbb{C}\to \mathbb{C}$ that have the property…

泛函分析 · 数学 2024-11-27 Paul Geuchen , Thomas Jahn , Hannes Matt

Recently, versions of neural networks with infinite-dimensional affine operators inside the computational units (``neural operator'' networks) have been applied to learn solutions to differential equations. To enable practical computations,…

泛函分析 · 数学 2026-02-03 Vinícius Luz Oliveira , Vladimir G. Pestov

The universal approximation theorem states that a neural network with one hidden layer can approximate continuous functions on compact sets with any desired precision. This theorem supports using neural networks for various applications,…

机器学习 · 计算机科学 2024-08-13 Marcos Eduardo Valle , Wington L. Vital , Guilherme Vieira

We develop a general framework for data-driven approximation of input-output maps between infinite-dimensional spaces. The proposed approach is motivated by the recent successes of neural networks and deep learning, in combination with…

Neural network width and depth are fundamental aspects of network topology. Universal approximation theorems provide that with increasing width or depth, there exists a neural network that approximates a function arbitrarily well. These…

机器学习 · 计算机科学 2019-10-31 Ibrohim Nosirov , Jeffrey M. Hokanson

Universal approximation theorems provide a mathematical explanation for the expressive power of neural networks. They assert that, under mild conditions on the activation function, feedforward neural networks are dense in broad function…

机器学习 · 计算机科学 2026-05-21 Soumendu Sundar Mukherjee , Himasish Talukdar

Universal approximation theory offers a foundational framework to verify neural network expressiveness, enabling principled utilization in real-world applications. However, most existing theoretical constructions are established by…

机器学习 · 计算机科学 2026-01-27 ZeYu Li , ShiJun Zhang , TieYong Zeng , FengLei Fan

While it is widely known that neural networks are universal approximators of continuous functions, a less known and perhaps more powerful result is that a neural network with a single hidden layer can approximate accurately any nonlinear…

机器学习 · 计算机科学 2021-11-03 Lu Lu , Pengzhan Jin , George Em Karniadakis

The classical development of neural networks has primarily focused on learning mappings between finite dimensional Euclidean spaces or finite sets. We propose a generalization of neural networks to learn operators, termed neural operators,…

Neural operator architectures approximate operators between infinite-dimensional Banach spaces of functions. They are gaining increased attention in computational science and engineering, due to their potential both to accelerate…

数值分析 · 数学 2024-06-18 Samuel Lanthaler , Zongyi Li , Andrew M. Stuart
‹ 上一页 1 2 3 10 下一页 ›