English
Related papers

Related papers: Approximation results on neural network operators …

200 papers

We introduce a new class of neural networks designed to be convex functions of their inputs, leveraging the principle that any convex function can be represented as the supremum of the affine functions it dominates. These neural networks,…

Machine Learning · Statistics 2024-11-21 Vincent Lemaire , Gilles Pagès , Christian Yeo

This paper explores the asymptotic behavior of univariate neural network operators, with an emphasis on both classical and fractional differentiation over infinite domains. The analysis leverages symmetrized and perturbed hyperbolic tangent…

General Mathematics · Mathematics 2025-02-12 Rômulo Damasclin Chaves dos Santos

In this article, the approximation properties of the Szasz-Mirakjan type operators are studied for the function of two variables, and the rate of convergence of the bivariate operators is determined in terms of total and partial modulus of…

Functional Analysis · Mathematics 2020-05-27 Rishikesh Yadav , Ramakanta Meher , Vishnu Narayan Mishra

We study a conical extension of averaged nonexpansive operators and the role it plays in convergence analysis of fixed point algorithms. Various properties of conically averaged operators are systematically investigated, in particular, the…

Optimization and Control · Mathematics 2020-12-01 Sedi Bartz , Minh N. Dao , Hung M. Phan

Transformers, and the attention mechanism in particular, have become ubiquitous in machine learning. Their success in modeling nonlocal, long-range correlations has led to their widespread adoption in natural language processing, computer…

Machine Learning · Computer Science 2025-12-23 Edoardo Calvello , Nikola B. Kovachki , Matthew E. Levine , Andrew M. Stuart

A new class of operators, larger than $C$-symmetric operators and different than normal one, named $C$--normal operators is introduced. Basic properties are given. Characterizations of this operators in finite dimensional spaces using a…

Functional Analysis · Mathematics 2020-01-01 Marek Ptak , Katarzyna Simik , Anna Wicher

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

We consider the representation of operators in terms of tensor networks and their application to ground-state approximation and time evolution of systems with long-range interactions. We provide an explicit construction to represent an…

Quantum Physics · Physics 2010-07-20 F. Fröwis , V. Nebendahl , W. Dür

Convolution is a broadly useful operation with applications including signal processing, machine learning, probability, optics, polynomial multiplication, and efficient parsing. Usually, however, this operation is understood and implemented…

Programming Languages · Computer Science 2019-03-27 Conal Elliott

In this paper, we introduce and study a new class of bounded linear operators on complex Hilbert spaces, which we call 2-C-normal operators. This class is inspired by and closely related to the notion of 2-normal operators, with additional…

Functional Analysis · Mathematics 2025-10-09 Messaoud Guesba , Ismail Lakehal , Sid Ahmed Ould Ahmed Mahmoud

We study the family of functions that are represented by a linear convolutional neural network (LCN). These functions form a semi-algebraic subset of the set of linear maps from input space to output space. In contrast, the families of…

Machine Learning · Computer Science 2022-06-09 Kathlén Kohn , Thomas Merkh , Guido Montúfar , Matthew Trager

In this paper, we introduce a Kantorovich type generalization of q-Bernstein-Stancu operators. We study the convergence of the introduced operators and also obtain the rate of convergence by these operators in terms of the modulus of…

Classical Analysis and ODEs · Mathematics 2015-05-27 M. Mursaleen , Khursheed J. Ansari , Asif Khan

In the present article, we propose the new class positive linear operators, which discrete type depending on a real parameters. These operators are similar to Jain operators but its approximation properties are different then Jain…

Classical Analysis and ODEs · Mathematics 2019-04-19 Prashantkumar Patel

We propose a novel technique for faster deep neural network training which systematically applies sample-based approximation to the constituent tensor operations, i.e., matrix multiplications and convolutions. We introduce new sampling…

Machine Learning · Computer Science 2021-10-27 Menachem Adelman , Kfir Y. Levy , Ido Hakimi , Mark Silberstein

Covering is an important type of data structure while covering-based rough sets provide an efficient and systematic theory to deal with covering data. In this paper, we use boolean matrices to represent and axiomatize three types of…

Artificial Intelligence · Computer Science 2013-03-05 Shiping Wang , Qingxin Zhu , William Zhu , Fan Min

Many neural networks for graphs are based on the graph convolution operator, proposed more than a decade ago. Since then, many alternative definitions have been proposed, that tend to add complexity (and non-linearity) to the model. In this…

Machine Learning · Computer Science 2021-06-11 Luca Pasa , Nicolò Navarin , Wolfgang Erb , Alessandro Sperduti

Neural networks have revolutionized the field of data science, yielding remarkable solutions in a data-driven manner. For instance, in the field of mathematical imaging, they have surpassed traditional methods based on convex…

Spectral Theory · Mathematics 2022-08-16 Leon Bungert , Ester Hait-Fraenkel , Nicolas Papadakis , Guy Gilboa

Dense prediction tasks typically employ encoder-decoder architectures, but the prevalent convolutions in the decoder are not image-adaptive and can lead to boundary artifacts. Different generalized convolution operations have been…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Anne S. Wannenwetsch , Martin Kiefel , Peter V. Gehler , Stefan Roth

Generative models for 3D geometric data arise in many important applications in 3D computer vision and graphics. In this paper, we focus on 3D deformable shapes that share a common topological structure, such as human faces and bodies.…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Giorgos Bouritsas , Sergiy Bokhnyak , Stylianos Ploumpis , Michael Bronstein , Stefanos Zafeiriou

Operator learning is a recent development in the simulation of Partial Differential Equations (PDEs) by means of neural networks. The idea behind this approach is to learn the behavior of an operator, such that the resulting neural network…

Numerical Analysis · Mathematics 2025-01-15 Ahmed Abdeljawad , Thomas Dittrich