English
Related papers

Related papers: On shallow feedforward neural networks with inputs…

200 papers

We establish upper bounds for the minimal number of hidden units for which a binary stochastic feedforward network with sigmoid activation probabilities and a single hidden layer is a universal approximator of Markov kernels. We show that…

Machine Learning · Computer Science 2015-03-26 Guido Montufar

While deep learning is successful in a number of applications, it is not yet well understood theoretically. A satisfactory theoretical characterization of deep learning however, is beginning to emerge. It covers the following questions: 1)…

Machine Learning · Computer Science 2019-08-27 Tomaso Poggio , Andrzej Banburski , Qianli Liao

The problem of extending a function $f$ defined on a training data $\mathcal{C}$ on an unknown manifold $\mathbb{X}$ to the entire manifold and a tubular neighborhood of this manifold is considered in this paper. For $\mathbb{X}$ embedded…

Machine Learning · Computer Science 2016-07-26 Charles K. Chui , H. N. Mhaskar

Invertible neural networks based on coupling flows (CF-INNs) have various machine learning applications such as image synthesis and representation learning. However, their desirable characteristics such as analytic invertibility come at the…

Machine Learning · Computer Science 2020-11-05 Takeshi Teshima , Isao Ishikawa , Koichi Tojo , Kenta Oono , Masahiro Ikeda , Masashi Sugiyama

We explore the approximation capabilities of Transformer networks for H\"older and Sobolev functions, and apply these results to address nonparametric regression estimation with dependent observations. First, we establish novel upper bounds…

Machine Learning · Statistics 2025-04-17 Yuling Jiao , Yanming Lai , Defeng Sun , Yang Wang , Bokai Yan

In this paper, feedforward neural networks are presented that have nonlinear weight functions based on look--up tables, that are specially smoothed in a regularization called the diffusion. The idea of such a type of networks is based on…

Neural and Evolutionary Computing · Computer Science 2007-05-23 Artur Rataj

A feed-forward neural network has a remarkable property which allows the network itself to be a universal approximator for any functions.Here we present a universal, machine-learning based solver for multi-variable partial differential…

Disordered Systems and Neural Networks · Physics 2018-11-14 Qianshi Wei , Ying Jiang , Jeff Z. Y. Chen

Deep learning models have achieved state-of-the-art performance in many classification tasks. However, most of them cannot provide an interpretation for their classification results. Machine learning models that are interpretable are…

Machine Learning · Computer Science 2021-11-04 Miles Q. Li , Benjamin C. M. Fung , Adel Abusitta

The regression of a functional response on a set of scalar predictors can be a challenging task, especially if there is a large number of predictors, or the relationship between those predictors and the response is nonlinear. In this work,…

Machine Learning · Statistics 2023-08-24 Sidi Wu , Cédric Beaulac , Jiguo Cao

It has been proposed that random wide neural networks near Gaussian process are quantum field theories around Gaussian fixed points. In this paper, we provide a novel map with which a wide class of quantum mechanical systems can be cast…

High Energy Physics - Theory · Physics 2024-03-19 Koji Hashimoto , Yuji Hirono , Jun Maeda , Jojiro Totsuka-Yoshinaka

Many practical problems need the output of a machine learning model to satisfy a set of constraints, $K$. Nevertheless, there is no known guarantee that classical neural network architectures can exactly encode constraints while…

Machine Learning · Computer Science 2022-02-10 Anastasis Kratsios , Behnoosh Zamanlooy , Tianlin Liu , Ivan Dokmanić

This paper studies the approximation capabilities of neural networks that combine layer normalization (LN) with linear layers. We prove that networks consisting of two linear layers with parallel layer normalizations (PLNs) inserted between…

Machine Learning · Computer Science 2026-02-10 Yunhao Ni , Yuxin Guo , Yuhe Liu , Wenxin Sun , Jie Luo , Wenjun Wu , Lei Huang

One of the most influential results in neural network theory is the universal approximation theorem [1, 2, 3] which states that continuous functions can be approximated to within arbitrary accuracy by single-hidden-layer feedforward neural…

Machine Learning · Computer Science 2021-12-16 Clemens Hutter , Recep Gül , Helmut Bölcskei

We present a new neural network to approximate convex functions. This network has the particularity to approximate the function with cuts and can be easily adapted to partial convexity. We give an universal approximation theorem in the full…

Optimization and Control · Mathematics 2023-01-27 Xavier Warin

Neural network models generally involve two important components, i.e., network architecture and neuron model. Although there are abundant studies about network architectures, only a few neuron models have been developed, such as the MP…

Machine Learning · Computer Science 2022-10-21 Jin-Hui Wu , Shao-Qun Zhang , Yuan Jiang , Zhi-Hua Zhou

The increasing demand on precision and throughput within high-precision mechatronics industries requires a new generation of feedforward controllers with higher accuracy than existing, physics-based feedforward controllers. As neural…

Systems and Control · Electrical Eng. & Systems 2024-01-26 Max Bolderman , Hans Butler , Sjirk Koekebakker , Eelco van Horssen , Ramidin Kamidi , Theresa Spaan-Burke , Nard Strijbosch , Mircea Lazar

We present a complete theoretical and empirical framework establishing feedforward neural networks as universal finite-state machines (N-FSMs). Our results prove that finite-depth ReLU and threshold networks can exactly simulate…

Machine Learning · Computer Science 2025-05-30 Sahil Rajesh Dhayalkar

We prove the converse of the universal approximation theorem, i.e. a neural network (NN) encoding theorem which shows that for every stably converged NN of continuous activation functions, its weight matrix actually encodes a continuous…

Machine Learning · Computer Science 2023-09-13 Ng Shyh-Chang , A-Li Luo , Bo Qiu

A feed-forward neural network is demonstrated to efficiently unfold the energy distribution of protons and alpha particles passing through passive material. This model-independent approach works with unbinned data and does not require…

High Energy Physics - Experiment · Physics 2021-12-16 Ming-Liang Wong , Andrew Edmonds , Chen Wu

The purpose of this article is to develop a machinery to study the capacity of deep neural networks (DNNs) to approximate high-dimensional functions. In particular, we show that DNNs have the expressive power to overcome the curse of…

Numerical Analysis · Mathematics 2026-04-30 Pierfrancesco Beneventano , Patrick Cheridito , Robin Graeber , Arnulf Jentzen , Benno Kuckuck