Results 21 to 30 of about 169,109 (267)

KOLMOGOROV'S SPLINE NETWORK [PDF]

open access: yesIEEE Transactions on Neural Networks, 2003
In this paper, an innovative neural-network architecture is proposed and elucidated. This architecture, based on the Kolmogorov's superposition theorem (1957) and called the Kolmogorov's spline network (KSN), utilizes more degrees of adaptation to data than currently used neural-network architectures (NNAs).
B, Igelnik, N, Parikh
openaire   +2 more sources

Quasi‐interpolation by splines on the uniform knot sets

open access: yesMathematical Modelling and Analysis, 2007
In the case of uniform grids, the error of the spline interpolant of a function defined on R has been well estimated. On the basis of the spline interpolation formula for functions defined on R we derive quasi‐interpolation formulae for functions defined
Evely Leetma
doaj   +1 more source

Group-Lasso on Splines for Spectrum Cartography [PDF]

open access: yes, 2010
The unceasing demand for continuous situational awareness calls for innovative and large-scale signal processing algorithms, complemented by collaborative and adaptive sensing platforms to accomplish the objectives of layered sensing and control. Towards
Georgios B. Giannakis   +4 more
core   +1 more source

L-Splines

open access: yesNumerische Mathematik, 1967
In this paper, we study the problem of unique interpolation and approximation by a class of spline functions,L-splines, containing as special cases the deficient and generalized spline functions ofAhlberg, Nilson, andWalsh [3, 5, 6], the Chebyshevian spline functions ofKarlin andZiegler [27], and the piecewise Hermite polynomial functions, as ...
VARGA, R.S., SCHULTZ, M.H.
openaire   +1 more source

Shallow Univariate ReLU Networks as Splines: Initialization, Loss Surface, Hessian, and Gradient Flow Dynamics

open access: yesFrontiers in Artificial Intelligence, 2022
Understanding the learning dynamics and inductive bias of neural networks (NNs) is hindered by the opacity of the relationship between NN parameters and the function represented.
Justin Sahs   +8 more
doaj   +1 more source

L’epoca delle splines: geometrie e linee del progetto contemporaneo

open access: yesDisegnare con, 2012
L’iconografia dell’architettura e del design di ogni epoca si caratterizza per l’uso di linee e di forme geometriche che vengono rese realizzabili dall’evoluzione dei materiali e delle tecniche costruttive, nonché dall’introduzione di particolari ...
Enrico Cicalò   +3 more
doaj   +1 more source

A Generic Multivariate Framework for the Integration of Microbiome Longitudinal Studies With Other Data Types

open access: yesFrontiers in Genetics, 2019
Simultaneous profiling of biospecimens using different technological platforms enables the study of many data types, encompassing microbial communities, omics, and meta-omics as well as clinical or chemistry variables.
Antoine Bodein   +3 more
doaj   +1 more source

Semialgebraic splines

open access: yesComputer Aided Geometric Design, 2017
25 pages, 6 ...
Michael DiPasquale   +2 more
openaire   +2 more sources

What are the limits of efficiency for the application of bi-cubic splines in a regional weather prediction grid point model?

open access: yesMeteorologische Zeitschrift, 2000
Single (one-dimensional) and bi-cubic (two-dimensional) splines have been used in numerical weather prediction models since about 1970. Especially the semi-Lagrangian advection schemes have been developed with the help of the spline interpolation method.
Thomas Prenosil, H.G. Becker
doaj   +1 more source

Fast spline quasicollocation solvers of integral equations

open access: yesMathematical Modelling and Analysis, 2007
A fast (C, Cm) solver for linear Fredholm integral equations u = Tu+f with smooth data is constructed on the basis of a discrete version of the spline quasicollocation method.
Gennadi Vainikko, Indrek Zolk
doaj   +1 more source

Home - About - Disclaimer - Privacy