English
Related papers

Related papers: Parallel Layer Normalization for Universal Approxi…

200 papers

Batch Normalization (BN) improves both convergence and generalization in training neural networks. This work understands these phenomena theoretically. We analyze BN by using a basic block of neural networks, consisting of a kernel layer, a…

Machine Learning · Computer Science 2019-04-25 Ping Luo , Xinjiang Wang , Wenqi Shao , Zhanglin Peng

Randomized neural networks (NNs) are an interesting alternative to conventional NNs that are more used for data modeling. The random vector functional-link (RVFL) network is an established and theoretically well-grounded randomized learning…

Computation · Statistics 2018-04-24 Hien D. Nguyen , Dianhui Wang , Geoffrey J. McLachlan

Topological Neural Networks (TNNs) incorporate higher-order relational information beyond pairwise interactions, enabling richer representations than Graph Neural Networks (GNNs). Concurrently, topological descriptors based on persistent…

Machine Learning · Computer Science 2024-06-06 Yogesh Verma , Amauri H Souza , Vikas Garg

The ubiquity of neural networks (NNs) in real-world applications, from healthcare to natural language processing, underscores their immense utility in capturing complex relationships within high-dimensional data. However, NNs come with…

Machine Learning · Computer Science 2024-07-08 Chang Yue , Niraj K. Jha

There has been a recent shift in sequence-to-sequence modeling from recurrent network architectures to convolutional network architectures due to computational advantages in training and operation while still achieving competitive…

Machine Learning · Computer Science 2019-10-29 Joshua Hanson , Maxim Raginsky

The developments of deep neural networks (DNN) in recent years have ushered a brand new era of artificial intelligence. DNNs are proved to be excellent in solving very complex problems, e.g., visual recognition and text understanding, to…

Machine Learning · Computer Science 2018-12-27 Qiang Hu , Hao Zhang

We address a learning-to-normalize problem by proposing Switchable Normalization (SN), which learns to select different normalizers for different normalization layers of a deep neural network. SN employs three distinct scopes to compute…

Computer Vision and Pattern Recognition · Computer Science 2019-07-25 Ping Luo , Ruimao Zhang , Jiamin Ren , Zhanglin Peng , Jingyu Li

Universality results for equivariant neural networks remain rare. Those that do exist typically hold only in restrictive settings: either they rely on regular or higher-order tensor representations, leading to impractically high-dimensional…

Machine Learning · Statistics 2025-10-20 Marco Pacini , Mircea Petrache , Bruno Lepri , Shubhendu Trivedi , Robin Walters

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…

Numerical Analysis · Mathematics 2021-01-01 Ronald DeVore , Boris Hanin , Guergana Petrova

Deep neural networks' remarkable ability to correctly fit training data when optimized by gradient-based algorithms is yet to be fully understood. Recent theoretical results explain the convergence for ReLU networks that are wider than…

Machine Learning · Computer Science 2021-02-09 Asaf Noy , Yi Xu , Yonathan Aflalo , Lihi Zelnik-Manor , Rong Jin

Recently, the interpretability of deep learning has attracted a lot of attention. A plethora of methods have attempted to explain neural networks by feature visualization, saliency maps, model distillation, and so on. However, it is hard…

Machine Learning · Computer Science 2021-10-19 Hangcheng Dong , Jingxiao Liao , Yan Wang , Yixin Chen , Bingguo Liu , Dong Ye , Guodong Liu

We present a fully constructive analysis of deep ReLU neural networks for classification and function approximation tasks. First, we prove that any dataset with $N$ distinct points in $\mathbb{R}^d$ and $M$ output classes can be exactly…

Machine Learning · Statistics 2025-06-25 Martín Hernández , Enrique Zuazua

State-of-the-art neural networks can be trained to become remarkable solutions to many problems. But while these architectures can express symbolic, perfect solutions, trained models often arrive at approximations instead. We show that the…

Machine Learning · Computer Science 2025-09-09 Matan Abudy , Orr Well , Emmanuel Chemla , Roni Katzir , Nur Lan

Proximal operators are ubiquitous in inverse problems, commonly appearing as part of algorithmic strategies to regularize problems that are otherwise ill-posed. Modern deep learning models have been brought to bear for these tasks too, as…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Zhenghan Fang , Sam Buchanan , Jeremias Sulam

Normalization layers are one of the key building blocks for deep neural networks. Several theoretical studies have shown that batch normalization improves the signal propagation, by avoiding the representations from becoming collinear…

Machine Learning · Computer Science 2023-10-04 Alexandru Meterez , Amir Joudaki , Francesco Orabona , Alexander Immer , Gunnar Rätsch , Hadi Daneshmand

We algorithmically construct a two hidden layer feedforward neural network (TLFN) model with the weights fixed as the unit coordinate vectors of the $d$-dimensional Euclidean space and having $3d+2$ number of hidden neurons in total, which…

Neural and Evolutionary Computing · Computer Science 2021-01-25 Namig J. Guliyev , Vugar E. Ismailov

Deep Neural Networks (DNNs) are universal function approximators providing state-of- the-art solutions on wide range of applications. Common perceptual tasks such as speech recognition, image classification, and object tracking are now…

Machine Learning · Statistics 2017-11-08 Randall Balestriero , Richard Baraniuk

We study ReLU deep neural networks (DNNs) by investigating their connections with the hierarchical basis method in finite element methods. First, we show that the approximation schemes of ReLU DNNs for $x^2$ and $xy$ are composition…

Numerical Analysis · Mathematics 2022-08-09 Juncai He , Lin Li , Jinchao Xu

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…

Machine Learning · Computer Science 2024-09-26 Li Liu , Tengchao Yu , Heng Yong

This study explores the number of neurons required for a Rectified Linear Unit (ReLU) neural network to approximate multivariate monomials. We establish an exponential lower bound on the complexity of any shallow network approximating the…

Machine Learning · Computer Science 2023-05-17 Itai Shapira