English
Related papers

Related papers: Universal approximation property of ODENet and Res…

200 papers

Neural networks have the ability to serve as universal function approximators, but they are not interpretable and don't generalize well outside of their training region. Both of these issues are problematic when trying to apply standard…

Machine Learning · Computer Science 2023-08-21 Colby Fronk , Linda Petzold

Unlike classical artificial neural networks, which require retraining for each new set of parametric inputs, the Deep Operator Network (DeepONet), a lately introduced deep learning framework, approximates linear and nonlinear solution…

Computational Engineering, Finance, and Science · Computer Science 2024-03-25 Shashank Kushwaha , Jaewan Park , Seid Koric , Junyan He , Iwona Jasiuk , Diab Abueidda

In this paper we prove that, in the deep limit, the stochastic gradient descent on a ResNet type deep neural network, where each layer shares the same weight matrix, converges to the stochastic gradient descent for a Neural ODE and that the…

Machine Learning · Statistics 2020-01-22 Benny Avelin , Kaj Nyström

We introduce a technique that enables Neural-ODEs to approximate arbitrary velocity fields with a priori planted fixed-points. Specifically, a recipe is given to explicitly accommodate for a finite collection of points in the reference…

Disordered Systems and Neural Networks · Physics 2026-05-12 Feliciano Giuseppe Pacifico , Duccio Fanelli , Lorenzo Buffoni , Lorenzo Chicchi , Diego Febbe , Raffaele Marino

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…

Functional Analysis · Mathematics 2022-05-18 Fred Espen Benth , Nils Detering , Luca Galimberti

Training deep neural networks with stochastic gradient descent (SGD) can often achieve zero training loss on real-world tasks although the optimization landscape is known to be highly non-convex. To understand the success of SGD for…

Machine Learning · Statistics 2020-06-15 Yiping Lu , Chao Ma , Yulong Lu , Jianfeng Lu , Lexing Ying

Residual networks (ResNets) have displayed impressive results in pattern recognition and, recently, have garnered considerable theoretical interest due to a perceived link with neural ordinary differential equations (neural ODEs). This link…

Machine Learning · Computer Science 2021-06-11 Alain-Sam Cohen , Rama Cont , Alain Rossier , Renyuan Xu

Neural networks are one of the most popularly used methods in machine learning and artificial intelligence nowadays. Due to the universal approximation theorem (Hornik et al. (1989)), a neural network with one hidden layer can approximate…

Statistics Theory · Mathematics 2019-09-18 Xiaoxi Shen , Chang Jiang , Lyudmila Sakhanenko , Qing Lu

The universal approximation theorem asserts that a single hidden layer neural network approximates continuous functions with any desired precision on compact sets. As an existential result, the universal approximation theorem supports the…

Machine Learning · Computer Science 2023-09-15 Wington L. Vital , Guilherme Vieira , Marcos Eduardo Valle

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…

Machine Learning · Computer Science 2020-10-30 Bhaavan Goel

We establish convergence of the training dynamics of residual neural networks (ResNets) to their joint infinite depth L, hidden width M, and embedding dimension D limit. Specifically, we consider ResNets with two-layer perceptron blocks in…

Machine Learning · Statistics 2026-03-23 Louis-Pierre Chaintron , Lénaïc Chizat , Javier Maass

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we…

Machine Learning · Computer Science 2020-01-09 Gao Huang , Zhuang Liu , Geoff Pleiss , Laurens van der Maaten , Kilian Q. Weinberger

We introduce a class of fully-connected neural networks whose activation functions, rather than being pointwise, rescale feature vectors by a function depending only on their norm. We call such networks radial neural networks, extending…

Machine Learning · Computer Science 2023-02-17 Iordan Ganev , Twan van Laarhoven , Robin Walters

Deep neural networks are highly expressive machine learning models with the ability to interpolate arbitrary datasets. Deep nets are typically optimized via first-order methods and the optimization process crucially depends on the…

Machine Learning · Statistics 2019-11-12 Talha Cihad Gulcu

Fast and accurate predictions for complex physical dynamics are a significant challenge across various applications. Real-time prediction on resource-constrained hardware is even more crucial in real-world problems. The deep operator…

Machine Learning · Computer Science 2023-12-27 Jae Yong Lee , Sung Woong Cho , Hyung Ju Hwang

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…

Functional Analysis · Mathematics 2022-12-13 Felix Voigtlaender

We investigate the expressive power of deep residual neural networks idealized as continuous dynamical systems through control theory. Specifically, we consider two properties that arise from supervised learning, namely universal…

Machine Learning · Computer Science 2023-09-13 Jingpu Cheng , Qianxiao Li , Ting Lin , Zuowei Shen

Complex-valued neural networks have attracted increasing attention in recent years, while it remains open on the advantages of complex-valued neural networks in comparison with real-valued networks. This work takes one step on this…

Machine Learning · Computer Science 2022-07-04 Shao-Qun Zhang , Wei Gao , Zhi-Hua Zhou

Neural Operator Networks (ONets) represent a novel advancement in machine learning algorithms, offering a robust and generalizable alternative for approximating partial differential equations (PDEs) solutions. Unlike traditional Neural…

Machine Learning · Computer Science 2024-04-30 Kazuma Kobayashi , James Daniell , Syed Bahauddin Alam

Continuous-depth neural networks, such as Neural ODEs, have refashioned the understanding of residual neural networks in terms of non-linear vector-valued optimal control problems. The common solution is to use the adjoint sensitivity…

Machine Learning · Computer Science 2022-02-16 Andrew Corbett , Dmitry Kangin