中文
相关论文

相关论文: A Unified and Constructive Framework for the Unive…

200 篇论文

Artificial neural networks (ANN), typically referred to as neural networks, are a class of Machine Learning algorithms and have achieved widespread success, having been inspired by the biological structure of the human brain. Neural…

机器学习 · 计算机科学 2022-04-08 Murilo Gustineli

Activation functions are non-linearities in neural networks that allow them to learn complex mapping between inputs and outputs. Typical choices for activation functions are ReLU, Tanh, Sigmoid etc., where the choice generally depends on…

To verify safety and robustness of neural networks, researchers have successfully applied abstract interpretation, primarily using the interval abstract domain. In this paper, we study the theoretical power and limits of the interval domain…

机器学习 · 计算机科学 2022-01-20 Zi Wang , Aws Albarghouthi , Gautam Prakriya , Somesh Jha

We generalize the classical universal approximation theorem for neural networks to the case of complex-valued neural networks. Precisely, we consider feedforward networks with a complex activation function $\sigma : \mathbb{C} \to…

泛函分析 · 数学 2022-12-13 Felix Voigtlaender

The universal approximation property of various machine learning models is currently only understood on a case-by-case basis, limiting the rapid development of new theoretically justified neural network architectures and blurring our…

机器学习 · 统计学 2020-12-01 Anastasis Kratsios

Deep learning architectures are highly diverse. To prove their universal approximation properties, existing works typically rely on model-specific proofs. Generally, they construct a dedicated mathematical formulation for each architecture…

机器学习 · 计算机科学 2025-11-12 Wei Wang

Neural networks (NNs) are known for their high predictive accuracy in complex learning problems. Beside practical advantages, NNs also indicate favourable theoretical properties such as universal approximation (UA) theorems. Binarized…

机器学习 · 计算机科学 2021-02-05 Mikail Yayla , Mario Günzel , Burim Ramosaj , Jian-Jia Chen

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

Neural networks are universal function approximators which are known to generalize well despite being dramatically overparameterized. We study this phenomenon from the point of view of the spectral bias of neural networks. Our contributions…

机器学习 · 计算机科学 2022-09-07 Qingguo Hong , Jonathan W. Siegel , Qinyang Tan , Jinchao Xu

Within the limited scope of this paper, we argue that artificial general intelligence cannot emerge from current neural network paradigms regardless of scale, nor is such an approach healthy for the field at present. Drawing on various…

人工智能 · 计算机科学 2025-11-25 Khanh Gia Bui

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 success of Neural networks in providing miraculous results when applied to a wide variety of tasks is astonishing. Insight in the working can be obtained by studying the universal approximation property of neural networks. It is proved…

机器学习 · 计算机科学 2021-11-17 R Subhash Chandra Bose , Kakarla Yaswanth

The classical Universal Approximation Theorem holds for neural networks of arbitrary width and bounded depth. Here we consider the natural `dual' scenario for networks of bounded width and arbitrary depth. Precisely, let $n$ be the number…

机器学习 · 计算机科学 2020-06-09 Patrick Kidger , Terry Lyons

In this paper, we develop a wavelet-based theoretical framework for analyzing the universal approximation capabilities of neural networks over a wide range of activation functions. Leveraging wavelet frame theory on the spaces of…

机器学习 · 计算机科学 2025-04-24 Youngmi Hur , Hyojae Lim , Mikyoung Lim

Although neural networks traditionally are typically used to approximate functions defined over $\mathbb{R}^n$, the successes of graph neural networks, point-cloud neural networks, and manifold deep learning among other methods have…

神经与进化计算 · 计算机科学 2019-07-11 Stella Rose Biderman

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

Neural Networks (NNs) are the method of choice for building learning algorithms. Their popularity stems from their empirical success on several challenging learning problems. However, most scholars agree that a convincing theoretical…

数值分析 · 数学 2021-01-01 Ronald DeVore , Boris Hanin , Guergana Petrova

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 universality of a quantum neural network refers to its ability to approximate arbitrary functions and is a theoretical guarantee for its effectiveness. A non-universal neural network could fail in completing the machine learning task.…

量子物理 · 物理学 2023-06-27 Xiaokai Hou , Guanyu Zhou , Qingyu Li , Shan Jin , Xiaoting Wang

Universal approximation theorem suggests that a shallow neural network can approximate any function. The input to neurons at each layer is a weighted sum of previous layer neurons and then an activation is applied. These activation…

机器学习 · 计算机科学 2020-10-30 Bhaavan Goel
‹ 上一页 1 2 3 10 下一页 ›