English
Related papers

Related papers: Approximation by neural network operators of convo…

200 papers

Quadratic operators are used in transforming the model Hamiltonian (H) of one correlated and dispersive band in an unique positive semidefinite form coopting both the kinetic and interacting part of H. The expression is used in deducing…

Strongly Correlated Electrons · Physics 2009-11-13 Istvan Chalupa , Zsolt Gulacsi

We derive bounds on the error, in high-order Sobolev norms, incurred in the approximation of Sobolev-regular as well as analytic functions by neural networks with the hyperbolic tangent activation function. These bounds provide explicit…

Numerical Analysis · Mathematics 2021-12-09 Tim De Ryck , Samuel Lanthaler , Siddhartha Mishra

By making use of some techniques based upon certain inverse new pairs of symbolic operators, the author investigate several decomposition formulas associated with Humbert hypergeometric functions $\Phi_1 $, $\Phi_2 $, $\Phi_3 $, $\Psi_1 $,…

Mathematical Physics · Physics 2008-10-22 A. Hasanov

By applying the derivative operator to the corresponding hypergeometric form of a $q$-series transformation due to Andrews [1,Theorem 4], we establish a general harmonic number identity. As the special cases of it, several interesting…

Combinatorics · Mathematics 2011-11-15 Chuanan Wei , Dianxuan Gong

This paper extends the classical theory of Voronovskaya-type asymptotic expansions to generalized neural network operators defined on non-Euclidean and fractal domains. We introduce and analyze smooth operators activated by modified and…

General Mathematics · Mathematics 2025-01-14 Rômulo Damasclin Chaves dos Santos , Jorge Henrique de Oliveira Sales

The approximate representation of operators by finite matrices is analysed in terms of accuracy and convergence. The identity operator, for example, can be reconstructed using a basis of harmonic oscillator states leading to a narrow peak…

Mathematical Physics · Physics 2025-12-02 B. G. Giraud , S. Karataglidis , K. Murulane , R. Peschanski

For a sequence of uniformly bounded, degenerate semigroups on a Hilbert space, we compare various types of convergences to a limit semigroup. Among others, we show that convergence of the semigroups, or of the resolvents of the generators,…

Functional Analysis · Mathematics 2016-09-02 R. Chill , A. F. M. ter Elst

Convolution and transposed convolution are fundamental operators widely used in neural networks. However, transposed convolution (a.k.a. deconvolution) does not serve as a true inverse of convolution due to inherent differences in their…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Xuhong Huang , Shiqi Liu , Kai Zhang , Ying Tai , Jian Yang , Hui Zeng , Lei Zhang

I continue the investigation of a q-analogue of the convolution on the line started in a joint work with Koornwinder and based on a formal definition due to Kempf and Majid. Two different ways of approximating functions by means of the…

Classical Analysis and ODEs · Mathematics 2016-09-07 Giovanna Carnovale

The goal of this work is to investigate the capability of a neural operator (DeepONet) to accurately capture the complex deformation of a platelet's membrane under shear flow. The surrogate model approximated by the neural operator predicts…

Computational Physics · Physics 2024-12-03 Marco Laudato , Luca Manzari , Khemraj Shukla

Convolution-type integral equations arise from various fields, \textit{e.g.}, finite impulse response filters in signal processing and deblurring problems in image processing. When solving these equations, conventional numerical methods,…

Numerical Analysis · Mathematics 2026-05-11 Raymond Chan , Lingfeng Li

Activation functions are key to effective backpropagation and expressiveness in deep neural networks. This work introduces Tangma, a new activation function that combines the smooth shape of the hyperbolic tangent with two learnable…

Neural and Evolutionary Computing · Computer Science 2025-07-16 Shreel Golwala

This paper outlines a covariant theory of operators defined on groups and homogeneous spaces. A systematic use of groups and their representations allows to obtain results of algebraic and analytical nature. The consideration is…

Representation Theory · Mathematics 2014-03-31 Vladimir V. Kisil

Convolution neural networks (CNNs) and Transformers have their own advantages and both have been widely used for dense prediction in multi-task learning (MTL). Most of the current studies on MTL solely rely on CNN or Transformer. In this…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Yangyang Xu , Yibo Yang , Lefei Zhang

We address the problem of phase shift operator acting as time evolution operator in Pegg-Barnett formalism. It is argued that standard shift operator is inconsistent with the behaviour of the state vector under cyclic evolution. We consider…

Quantum Physics · Physics 2007-05-23 Ramandeep S. Johal

Here we research the univariate quantitative approximation of real and complex valued continuous functions on a compact interval or all the real line by quasi-interpolation, Baskakov type and quadrature type neural network operators. We…

Classical Analysis and ODEs · Mathematics 2014-04-28 George Anastassiou

A general deformation of the Heisenberg algebra is introduced with two deformed operators instead of just one. This is generalised to many variables, and permits the simultaneous existence of coherent states, and the transposition of…

High Energy Physics - Theory · Physics 2009-10-22 D. B. Fairlie , J. Nuyts

The thesis comprises three chapters. Chapter 1 investigates generalizations of the theorem of Fatou for convolution type integral operators with general approximate identities. It is introduced $\lambda(r)$-convergence, which is a…

Classical Analysis and ODEs · Mathematics 2022-02-18 Mher Safaryan

Deep convolutional neural networks are being actively investigated in a wide range of speech and audio processing applications including speech recognition, audio event detection and computational paralinguistics, owing to their ability to…

Machine Learning · Computer Science 2018-01-16 Che-Wei Huang , Shrikanth. S. Narayanan

Novel types of convolution operators for quaternion linear canonical transform (QLCT) are proposed. Type one and two are defined in the spatial and QLCT spectral domains, respectively. They are distinct in the quaternion space and are…

Classical Analysis and ODEs · Mathematics 2022-12-13 Xiaoxiao Hu , Dong Cheng , Kit Ian Kou