中文
相关论文

相关论文: Deep Network with Approximation Error Being Recipr…

200 篇论文

This paper quantitatively characterizes the approximation power of deep feed-forward neural networks (FNNs) in terms of the number of neurons. It is shown by construction that ReLU FNNs with width $\mathcal{O}\big(\max\{d\lfloor…

数值分析 · 数学 2021-01-15 Zuowei Shen , Haizhao Yang , Shijun Zhang

This paper concentrates on the approximation power of deep feed-forward neural networks in terms of width and depth. It is proved by construction that ReLU networks with width $\mathcal{O}\big(\max\{d\lfloor N^{1/d}\rfloor,\, N+2\}\big)$…

机器学习 · 计算机科学 2021-12-15 Zuowei Shen , Haizhao Yang , Shijun Zhang

A three-hidden-layer neural network with super approximation power is introduced. This network is built with the floor function ($\lfloor x\rfloor$), the exponential function ($2^x$), the step function ($1_{x\geq 0}$), or their compositions…

机器学习 · 计算机科学 2021-04-27 Zuowei Shen , Haizhao Yang , Shijun Zhang

This paper establishes the (nearly) optimal approximation error characterization of deep rectified linear unit (ReLU) networks for smooth functions in terms of both width and depth simultaneously. To that end, we first prove that…

机器学习 · 计算机科学 2021-11-03 Jianfeng Lu , Zuowei Shen , Haizhao Yang , Shijun Zhang

We present SiLU network constructions whose approximation efficiency depends critically on proper hyperparameter tuning. For the square function $x^2$, with optimally chosen shift $a$ and scale $\beta$, we achieve approximation error…

机器学习 · 计算机科学 2026-02-24 Koffi O. Ayena

In this paper, we construct neural networks with ReLU, sine and $2^x$ as activation functions. For general continuous $f$ defined on $[0,1]^d$ with continuity modulus $\omega_f(\cdot)$, we construct ReLU-sine-$2^x$ networks that enjoy an…

机器学习 · 计算机科学 2022-08-16 Yuling Jiao , Yanming Lai , Xiliang Lu , Fengru Wang , Jerry Zhijian Yang , Yuanyuan Yang

Neural networks activated by the rectified linear unit (ReLU) play a central role in the recent development of deep learning. The topic of approximating functions from H\"older spaces by these networks is crucial for understanding the…

机器学习 · 计算机科学 2023-07-25 Tong Mao , Ding-Xuan Zhou

The paper briefy reviews several recent results on hierarchical architectures for learning from examples, that may formally explain the conditions under which Deep Convolutional Neural Networks perform much better in function approximation…

机器学习 · 计算机科学 2016-08-12 Hrushikesh Mhaskar , Tomaso Poggio

We study the computation complexity of deep ReLU (Rectified Linear Unit) neural networks for the approximation of functions from the H\"older-Zygmund space of mixed smoothness defined on the $d$-dimensional unit cube when the dimension $d$…

数值分析 · 数学 2021-07-26 Dinh Dũng , Van Kien Nguyen

We study the expressive power of deep ReLU neural networks for approximating functions in dilated shift-invariant spaces, which are widely used in signal processing, image processing, communications and so on. Approximation error bounds are…

机器学习 · 计算机科学 2023-12-05 Yunfei Yang , Zhen Li , Yang Wang

This article concerns the expressive power of depth in neural nets with ReLU activations and bounded width. We are particularly interested in the following questions: what is the minimal width $w_{\text{min}}(d)$ so that ReLU nets of width…

机器学习 · 统计学 2019-10-22 Boris Hanin

There has been a growing interest in expressivity of deep neural networks. However, most of the existing work about this topic focuses only on the specific activation function such as ReLU or sigmoid. In this paper, we investigate the…

机器学习 · 统计学 2019-07-24 Ilsang Ohn , Yongdai Kim

Whereas recovery of the manifold from data is a well-studied topic, approximation rates for functions defined on manifolds are less known. In this work, we study a regression problem with inputs on a $d^*$-dimensional manifold that is…

机器学习 · 统计学 2019-08-05 Johannes Schmidt-Hieber

We develop a geometric approximation theory for deep feed-forward neural networks with ReLU activations. Given a $d$-dimensional hypersurface in $\mathbb{R}^{d+1}$ represented as the graph of a $C^2$-function $\phi$, we show that a deep…

机器学习 · 计算机科学 2024-07-08 Jonatan Vallin , Karl Larsson , Mats G. Larson

We consider approximations of general continuous functions on finite-dimensional cubes by general deep ReLU neural networks and study the approximation rates with respect to the modulus of continuity of the function and the total number of…

神经与进化计算 · 计算机科学 2018-06-08 Dmitry Yarotsky

We discuss the expressive power of neural networks which use the non-smooth ReLU activation function $\varrho(x) = \max\{0,x\}$ by analyzing the approximation theoretic properties of such networks. The existing results mainly fall into two…

泛函分析 · 数学 2019-04-10 Felix Voigtlaender , Philipp Petersen

This article concerns the expressive power of depth in deep feed-forward neural nets with ReLU activations. Specifically, we answer the following question: for a fixed $d_{in}\geq 1,$ what is the minimal width $w$ so that neural nets with…

机器学习 · 统计学 2018-03-13 Boris Hanin , Mark Sellke

The foundations of deep learning are supported by the seemingly opposing perspectives of approximation or learning theory. The former advocates for large/expressive models that need not generalize, while the latter considers classes that…

机器学习 · 计算机科学 2025-06-27 Ruiyang Hong , Anastasis Kratsios

We study the size of a neural network needed to approximate the maximum function over $d$ inputs, in the most basic setting of approximating with respect to the $L_2$ norm, for continuous distributions, for a network that uses ReLU…

机器学习 · 计算机科学 2023-11-08 Itay Safran , Daniel Reichman , Paul Valiant

We discuss approximation of functions using deep neural nets. Given a function $f$ on a $d$-dimensional manifold $\Gamma \subset \mathbb{R}^m$, we construct a sparsely-connected depth-4 neural network and bound its error in approximating…

机器学习 · 统计学 2017-04-24 Uri Shaham , Alexander Cloninger , Ronald R. Coifman
‹ 上一页 1 2 3 10 下一页 ›