English
Related papers

Related papers: A Multiplicative Neural Network Architecture: Loca…

200 papers

This work focuses on the analysis of fully connected feed forward ReLU neural networks as they approximate a given, smooth function. In contrast to conventionally studied universal approximation properties under increasing architectures,…

Machine Learning · Computer Science 2024-06-24 Erion Morina , Martin Holler

A class of neural networks that gained particular interest in the last years are neural ordinary differential equations (neural ODEs). We study input-output relations of neural ODEs using dynamical systems theory and prove several results…

Dynamical Systems · Mathematics 2023-09-29 Christian Kuehn , Sara-Viola Kuntz

We introduce a new approach to processing complex-valued data using DNNs consisting of parallel real-valued subnetworks with coupled outputs. Our proposed class of architectures, referred to as Steinmetz Neural Networks, incorporates…

Machine Learning · Computer Science 2025-02-17 Shyam Venkatasubramanian , Ali Pezeshki , Vahid Tarokh

Quantifying similarity between neural representations -- e.g. hidden layer activation vectors -- is a perennial problem in deep learning and neuroscience research. Existing methods compare deterministic responses (e.g. artificial networks…

Machine Learning · Computer Science 2023-02-07 Lyndon R. Duong , Jingyang Zhou , Josue Nassar , Jules Berman , Jeroen Olieslagers , Alex H. Williams

In this work we demonstrate a novel separation between symmetric neural network architectures. Specifically, we consider the Relational Network~\parencite{santoro2017simple} architecture as a natural generalization of the…

Machine Learning · Computer Science 2022-12-13 Aaron Zweig , Joan Bruna

We develop a general framework for data-driven approximation of input-output maps between infinite-dimensional spaces. The proposed approach is motivated by the recent successes of neural networks and deep learning, in combination with…

Numerical Analysis · Mathematics 2021-06-21 Kaushik Bhattacharya , Bamdad Hosseini , Nikola B. Kovachki , Andrew M. Stuart

We analyze the universal approximation constraints of narrow Residual Neural Networks (ResNets) both theoretically and numerically. For deep neural networks without input space augmentation, a central constraint is the inability to…

Dynamical Systems · Mathematics 2026-03-31 Christian Kuehn , Sara-Viola Kuntz , Tobias Wöhrer

Representation learning of networks has witnessed significant progress in recent times. Such representations have been effectively used for classic network-based machine learning tasks like node classification, link prediction, and network…

Social and Information Networks · Computer Science 2018-12-07 Arunkumar Bagavathi , Siddharth Krishnan

In several domains, data objects can be decomposed into sets of simpler objects. It is then natural to represent each object as the set of its components or parts. Many conventional machine learning algorithms are unable to process this…

Machine Learning · Computer Science 2020-03-03 Konstantinos Skianis , Giannis Nikolentzos , Stratis Limnios , Michalis Vazirgiannis

The extent to which different biological and artificial neural systems rely on equivalent internal representations to support similar tasks remains a central question in neuroscience and machine learning. Prior work typically compares…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Jialin Wu , Shreya Saha , Yiqing Bo , Meenakshi Khosla

We introduce Neural Radiosity, an algorithm to solve the rendering equation by minimizing the norm of its residual similar as in traditional radiosity techniques. Traditional basis functions used in radiosity techniques, such as piecewise…

Graphics · Computer Science 2021-10-12 Saeed Hadadan , Shuhong Chen , Matthias Zwicker

We demonstrate that a very deep ResNet with stacked modules with one neuron per hidden layer and ReLU activation functions can uniformly approximate any Lebesgue integrable function in $d$ dimensions, i.e. $\ell_1(\mathbb{R}^d)$. Because of…

Machine Learning · Computer Science 2018-07-05 Hongzhou Lin , Stefanie Jegelka

In certain situations, neural networks are trained upon data that obey underlying symmetries. However, the predictions do not respect the symmetries exactly unless embedded in the network structure. In this work, we introduce architectures…

Machine Learning · Computer Science 2022-04-28 Anwesh Bhattacharya , Marios Mattheakis , Pavlos Protopapas

While artificial neural networks are known as universal approximators for continuous functions, many modern approaches rely on overparameterized architectures with high computational cost. In this work, we introduce the Barycentric Neural…

Machine Learning · Computer Science 2025-10-10 Victor Toscano-Duran , Rocio Gonzalez-Diaz , Miguel A. Gutiérrez-Naranjo

We develop a theoretical analysis for special neural network architectures, termed operator recurrent neural networks, for approximating nonlinear functions whose inputs are linear operators. Such functions commonly arise in solution…

Optimization and Control · Mathematics 2022-01-05 Maarten V. de Hoop , Matti Lassas , Christopher A. Wong

We give a geometric construction of neural networks that separate disjoint compact subsets of $\Bbb R^n$, and use it to obtain a constructive universal approximation theorem. Specifically, we show that networks with two hidden layers and…

Machine Learning · Computer Science 2026-02-16 Chanyoung Sung

Inner products of neural network feature maps arise in a wide variety of machine learning frameworks as a method of modeling relations between inputs. This work studies the approximation properties of inner products of neural networks. It…

Machine Learning · Computer Science 2024-06-18 Awni Altabaa , John Lafferty

In this work, we show that neural networks can be represented via the mathematical theory of quiver representations. More specifically, we prove that a neural network is a quiver representation with activation functions, a mathematical…

Machine Learning · Computer Science 2021-03-24 Marco Antonio Armenta , Pierre-Marc Jodoin

We consider projection algorithms for solving (nonconvex) feasibility problems in Euclidean spaces. Of special interest are the Method of Alternating Projections (MAP) and the Douglas-Rachford or Averaged Alternating Reflection Algorithm…

Optimization and Control · Mathematics 2014-03-17 Robert Hesse , D. Russell Luke

We describe generalizations of the universal approximation theorem for neural networks to maps invariant or equivariant with respect to linear representations of groups. Our goal is to establish network-like computational models that are…

Neural and Evolutionary Computing · Computer Science 2018-04-30 Dmitry Yarotsky
‹ Prev 1 3 4 5 6 7 10 Next ›