Search Results - "Maiorov, Vitaly"
-
1
On the optimality of neural-network approximation using incremental algorithms
Published in IEEE transactions on neural networks (01-03-2000)“…The problem of approximating functions by neural networks using incremental algorithms is studied. For functions belonging to a rather general class,…”
Get full text
Journal Article -
2
Geometric properties of the ridge function manifold
Published in Advances in computational mathematics (01-02-2010)“…We study geometrical properties of the ridge function manifold consisting of all possible linear combinations of n functions of the form g ( a · x ), where a ·…”
Get full text
Journal Article -
3
Lower bounds for approximation by MLP neural networks
Published in Neurocomputing (Amsterdam) (01-04-1999)“…The degree of approximation by a single hidden layer MLP model with n units in the hidden layer is bounded below by the degree of approximation by a linear…”
Get full text
Journal Article -
4
On best approximation of classes by radial functions
Published in Journal of approximation theory (2003)“…We investigate the radial manifolds R n generated by a linear combination of n radial functions on R d . We consider the best approximation of function classes…”
Get full text
Journal Article -
5
Lower bounds for multivariate approximation by affine-invariant dictionaries
Published in IEEE transactions on information theory (01-05-2001)“…The problem of approximating locally smooth multivariate functions by linear combinations of elements from an affine-invariant redundant dictionary is…”
Get full text
Journal Article -
6
On the Value of Partial Information for Learning from Examples
Published in Journal of Complexity (01-12-1997)“…The PAC model of learning and its extension to real valued function classes provides a well-accepted theoretical framework for representing the problem of…”
Get full text
Journal Article -
7
On the Learnability of Rich Function Classes
Published in Journal of computer and system sciences (01-02-1999)“…The probably approximately correct (PAC) model of learning and its extension to real-valued function classes sets a rigorous framework based upon which the…”
Get full text
Journal Article -
8
On the Approximation of Functional Classes Equipped with a Uniform Measure Using Ridge Functions
Published in Journal of approximation theory (01-07-1999)“…We introduce a construction of a uniform measure over a functional class Br which is similar to a Besov class with smoothness index r. We then consider the…”
Get full text
Journal Article -
9
The degree of approximation of sets in euclidean space using sets with bounded Vapnik-Chervonenkis dimension
Published in Discrete Applied Mathematics (18-08-1998)“…The degree of approximation of infinite-dimensional function classes using finite n-dimensional manifolds has been the subject of a classical field of study in…”
Get full text
Journal Article -
10
Error bounds for functional approximation and estimation using mixtures of experts
Published in IEEE transactions on information theory (01-05-1998)“…We examine some mathematical aspects of learning unknown mappings with the mixture of experts model (MEM). Specifically, we observe that the MEM is at least as…”
Get full text
Journal Article -
11
Distortion bounds for vector quantizers with finite codebook size
Published in IEEE transactions on information theory (01-07-1999)“…Upper and lower bounds are presented for the distortion of the optimal N-point vector quantizer applied to k-dimensional signals. Under certain smoothness…”
Get full text
Journal Article -
12
Approximation bounds for smooth functions in C(R/sup d/) by neural and mixture networks
Published in IEEE transactions on neural networks (01-09-1998)“…We consider the approximation of smooth multivariate functions in C(R/sup d/) by feedforward neural networks with a single hidden layer of nonlinear ridge…”
Get full text
Journal Article