Results 61 to 70 of about 1,777,436 (249)

Learnability in Hilbert Spaces with Reproducing Kernels

Journal of Complexity, 2002
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
openaire   +1 more source

Density Problem and Approximation Error in Learning Theory

Abstract and Applied Analysis, 2013
We study the density problem and approximation error of reproducing kernel Hilbert spaces for the purpose of learning theory. For a Mercer kernel on a compact metric space (, ), a characterization for the generated reproducing kernel Hilbert space (RKHS)
Ding-Xuan Zhou
doaj   +1 more source

Representing Functions in H² on the Kepler Manifold via WPOAFD Based on the Rational Approximation of Holomorphic Functions

Mathematics, 2022
The central problem of this study is to represent any holomorphic and square integrable function on the Kepler manifold in the series form based on Fourier analysis.
Zeyuan Song, Zuoren Sun
doaj   +1 more source

On the Use of Reproducing Kernel Hilbert Spaces in Functional Classification [PDF]

Journal of the American Statistical Association, 2015
The Hájek–Feldman dichotomy establishes that two Gaussian measures are either mutually absolutely continuous with respect to each other (and hence there is a Radon–Nikodym density for each measure with respect to the other one) or mutually singular ...
J. R. Berrendero, A. Cuevas, J. Torrecilla   +2 more
semanticscholar   +1 more source

Semi reproducing kernel hilbert spaces and mixed precision computation. [PDF]

, 2018
Positive definite and conditionally positive definite functions are widely used in interpolation and smoothing problems, particularly when the data is scattered.
Garing, Ronald
core   +1 more source

Reproducing Kernel Method for Solving Nonlinear Differential-Difference Equations

Abstract and Applied Analysis, 2012
On the basis of reproducing kernel Hilbert spaces theory, an iterative algorithm for solving some nonlinear differential-difference equations (NDDEs) is presented.
Reza Mokhtari, Fereshteh Toutian Isfahani, Maryam Mohammadi   +2 more
doaj   +1 more source

GPU-Accelerated Partially Linear Multiuser Detection for 5G and Beyond URLLC Systems

IEEE Access, 2022
We have implemented a recently proposed partially linear multiuser detection algorithm in reproducing kernel Hilbert spaces (RKHSs) on a GPU-accelerated platform.
Matthias Mehlhose, Guillermo Marcus, Daniel Schaufele, Daniyal Amir Awan, Nikolaus Binder, Martin Kasparick, Renato L. G. Cavalcante, Slawomir Stanczak, Alexander Keller   +8 more
doaj   +1 more source

Designing Wire Mazes for Replicating Natural Echoes to Study Bat Biosonar Function

Advanced Intelligent Systems, EarlyView.
A validated framework combining efficient physical modeling (multiple scattering model) and deep learning is presented to guide wire‐maze design for bat biosonar studies. This approach rapidly generates large datasets to test acoustic distinguishability among wire arrangements.
Chunlin Jia, Gengkai Hu, Boo Cheong Khoo, Rolf Müller   +3 more
wiley   +1 more source

A highly accurate numerical method for solving boundary value problem of generalized Bagley‐Torvik equation

Mathematical Methods in the Applied Sciences, EarlyView.
A highly accurate numerical method is given for the solution of boundary value problem of generalized Bagley‐Torvik (BgT) equation with Caputo derivative of order 0<β<2$$ 0<\beta <2 $$ by using the collocation‐shooting method (C‐SM). The collocation solution is constructed in the space Sm+1(1)$$ {S}_{m+1}^{(1)} $$ as piecewise polynomials of degree at ...
Suzan Cival Buranay, Mtema James Chin, Nazim I. Mahmudov   +2 more
wiley   +1 more source

Some Notes on Error Analysis for Kernel Based Regularized Interpolation

International Journal of Analysis and Applications, 2020
Kernel based regularized interpolation is one of the most important methods for approximating functions. The theory behind the kernel based regularized interpolation is the well-known Representer Theorem, which shows the form of approximation function in
Qing Zou
doaj