The Gaussian Radon transform and machine learning
نویسندگان
چکیده
منابع مشابه
The Gaussian Radon Transform for Banach Spaces
The classical Radon transform can be thought of as a way to obtain the density of an n-dimensional object from its (n− 1)-dimensional sections in di erent directions. A generalization of this transform to in nite-dimensional spaces has the potential to allow one to obtain a function de ned on an in nite-dimensional space from its conditional expectations. We work within a standard framework in ...
متن کاملThe Gaussian Radon Transform in Classical Wiener Space*
We study the Gaussian Radon transform in the classical Wiener space of Brownian motion. We determine explicit formulas for transforms of Brownian functionals specified by stochastic integrals. A Fock space decomposition is also established for Gaussian measure conditioned to closed affine subspaces in Hilbert spaces.
متن کاملThe Radon-gauss Transform
Gaussian measure is constructed for any given hyperplane in an infinite dimensional Hilbert space, and this is used to define a generalization of the Radon transform to the infinite dimensional setting, using Gauss measure instead of Lebesgue measure. An inversion formula is obtained and a support theorem proved.
متن کاملRadon transform and curvature
We interpret the setting for a Radon transform as a submanifold of the space of generalized functions, and compute its extrinsic curvature: it is the Hessian composed with the Radon transform. 1. The general setting. Let M and Σ be smooth finite dimensional manifolds. Let m = dim(M). A linear mapping R : C∞ c (M)→ C∞(Σ) is called a (generalized) Radon transform if it is given in the following w...
متن کاملGaussian Processes For Machine Learning
Gaussian processes (GPs) are natural generalisations of multivariate Gaussian random variables to infinite (countably or continuous) index sets. GPs have been applied in a large number of fields to a diverse range of ends, and very many deep theoretical analyses of various properties are available. This paper gives an introduction to Gaussian processes on a fairly elementary level with special ...
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: Infinite Dimensional Analysis, Quantum Probability and Related Topics
سال: 2015
ISSN: 0219-0257,1793-6306
DOI: 10.1142/s0219025715500198