Results 21 to 30 of about 373,199 (312)
Approximation of rough functions
Journal of Approximation Theory, 2016 16 pages, 3 ...
Michael F. Barnsley +3 more
openaire +4 more sources
An efficient hardware architecture for a neural network activation function generator [PDF]
, 2006 This paper proposes an efficient hardware architecture for a function generator suitable for an artificial neural network (ANN). A spline-based approximation function is designed that provides a good trade-off between accuracy and silicon area, whilst ...
Daniel Larkin +8 more
core +1 more source
Approximations to Kelvin Functions [PDF]
Mathematics of Computation, 1963 While preparing a digital computer program to examine the behavior of largetaper hub flanges, it was found necessary to use approximations to the Kelvin functions ber x, bei x, ker x, and kei x, and to their first derivatives. To obtain full machine accuracy, the approximations were required to be correct to nine significant figures.
openaire +2 more sources
Моделирование и анализ информационных систем, 2021 Let $G_{k}$ be defined as $G_{k} = \langle a, b;\ a^{-1}ba = b^{k} \rangle$, where $k \ne 0$. It is known that, if $p$ is some prime number, then $G_{k}$ is residually a finite $p$-group if and only if $p \mid k - 1$. It is also known that, if $p$ and $q$
Elena Alexandrovna Tumanova
doaj +1 more source
Approximate functional differencing
SERIEs, 2023 AbstractInference on common parameters in panel data models with individual-specific fixed effects is a classic example of Neyman and Scott’s (Econometrica 36:1–32, 1948) incidental parameter problem (IPP). One solution to this IPP is functional differencing (Bonhomme in Econometrica 80(4):1337–1385, 2012), which works when the number of time ...
Geert Dhaene, Martin Weidner
openaire +3 more sources
Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska, 2023 Artificial neural networks are essential intelligent tools for various learning tasks. Training them is challenging due to the nature of the data set, many training weights, and their dependency, which gives rise to a complicated high-dimensional error ...
Saithip Limtrakul +1 more
doaj +1 more source
Estimates of the Approximation Error Using Rademacher Complexity: Learning Vector-Valued Functions [PDF]
, 2008 For certain families of multivariable vector-valued functions to be approximated, the accuracy of approximation schemes made up of linear combinations of computational units containing adjustable parameters is investigated.
Gnecco Giorgio +7 more
core +1 more source
THE SOLUTION OF THE APPROXIMATION PROBLEM OF NONLINEAR DEPENDANCES USING ARTIFICIAL NEURAL NETWORKS
Научный вестник МГТУ ГА, 2018 The paper discusses issues connected with the use of an artificial neural network (ANN) to approximate the experimental data. One of the problems in the development of the ANN is the choice of an appropriate activation function for neurons of the hidden ...
V. N. Ageyev
doaj +1 more source
ON THE CONVERGENCE OF THE LEAST SQUARE METHOD IN CASE OF NON-UNIFORM GRIDS
Проблемы анализа, 2019 Let f(t) be a continuous on [−1, 1] function, which values are given at the points of arbitrary non-uniform grid ΩN = = {tj} N−1 j=0 , where nodes tj satisfy the only condition ηj 6tj 6ηj+1, 0 6 j 6 N − 1, and nodes ηj are such that −1 = η0 < η1 < η2
M. S. Sultanakhmedov
doaj +1 more source
Наука. Инновации. Технологии, 2022 Introduction: the methods of representation of functions given approximately by their singular integrals in relation to approximation problems and numerical methods for solving boundary value problems for differential equations are Investigated.
Igor Eduardovich Naats +2 more
doaj