Approximating Multivariable Functions by Feedforward Neural Nets

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F13%3A00389184" target="_blank" >RIV/67985807:_____/13:00389184 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.1007/978-3-642-36657-4_5" target="_blank" >http://dx.doi.org/10.1007/978-3-642-36657-4_5</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-642-36657-4_5" target="_blank" >10.1007/978-3-642-36657-4_5</a>

Result language

angličtina

Original language name

Approximating Multivariable Functions by Feedforward Neural Nets

Original language description

Theoretical results on approximation of multivariable functions by feedforward neural networks are surveyed. Some proofs of universal approximation capabilities of networks with perceptrons and radial units are sketched. Major tools for estimation of rates of decrease of approximation errors with increasing model complexity are proven. Properties of best approximation are discussed. Recent results on dependence of model complexity on input dimension are presented and some cases when multivariable functions can be tractably approximated are described.

Czech name

—

Czech description

—

Type

C - Chapter in a specialist book

CEP classification

IN - Informatics

OECD FORD branch

—

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2013

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Book/collection name

Handbook on Neural Information Processing

ISBN

978-3-642-36656-7

Number of pages of the result

39

Pages from-to

143-181

Number of pages of the book

499

Publisher name

Springer

Place of publication

Berlin

UT code for WoS chapter

—