Some Upper Bounds for RKHS Approximation by Bessel Functions
نویسندگان
چکیده
A reproducing kernel Hilbert space (RKHS) approximation problem arising from learning theory is investigated. Some K-functionals and moduli of smoothness with respect to RKHSs are defined Fourier–Bessel series transforms, respectively. Their equivalent relation shown, which the upper bound estimate for best RKHS provided. The convergence rate bounded modulus smoothness, shows that can attain same ability as transform. In particular, it shown a produced by Bessel operator, sums up corresponding convolution operator approximation. investigations show some new applications functions. results obtained be used error in theory.
منابع مشابه
Uniform Bounds for Bessel Functions
For ν > −1/2 and x real we shall establish explicit bounds for the Bessel function Jν(x) which are uniform in x and ν. This work and the recent result of L. J. Landau [7] provide relatively sharp inequalities for all real x.
متن کاملSome Integrals Involving Bessel Functions Some Integrals Involving Bessel Functions
A number of new definite integrals involving Bessel functions are presented. These have been derived by finding new integral representations for the product of two Bessel functions of different order and argument in terms of the generalized hypergeometric function with subsequent reduction to special cases. Connection is made with Weber's second exponential integral and Laplace transforms of pr...
متن کاملSome Inequalities for Modified Bessel Functions
We denote by Iν and Kν the Bessel functions of the first and third kind, respectively. Motivated by the relevance of the function wν t t Iν−1 t /Iν t , t > 0, in many contexts of applied mathematics and, in particular, in some elasticity problems Simpson and Spector 1984 , we establish new inequalities for Iν t /Iν−1 t . The results are based on the recurrence relations for Iν and Iν−1 and the ...
متن کاملLower Bounds for Approximation of Some Classes of Lebesgue Measurable Functions by Sigmoidal Neural Networks
We propose a general method for estimating the distance between a compact subspace K of the space L([0, 1]) of Lebesgue measurable functions defined on the hypercube [0, 1], and the class of functions computed by artificial neural networks using a single hidden layer, each unit evaluating a sigmoidal activation function. Our lower bounds are stated in terms of an invariant that measures the osc...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Axioms
سال: 2022
ISSN: ['2075-1680']
DOI: https://doi.org/10.3390/axioms11050233