Aproximation and learning of multivariable functions by neural networks
Public support
Provider
Ministry of Education, Youth and Sports
Programme
KONTAKT
Call for proposals
KONTAKT 8 (SMSM2010ME5)
Main participants
—
Contest type
VS - Public tender
Contract ID
2062/2011-320
Alternative language
Project name in Czech
Aproximace a učení funkcí mnoha proměnných pomocí neuronových sítí
Annotation in Czech
Cílem projektu je odvození teoretických výsledků a návrh a softwarová realizace učících algoritmů pro modely neurovýpočtů založených na aproximaci funkcí více proměnných.
Scientific branches
R&D category
ZV - Basic research
CEP classification - main branch
IN - Informatics
CEP - secondary branch
BA - General mathematics
CEP - another secondary branch
—
OECD FORD - equivalent branches <br>(according to the <a href="http://www.vyzkum.cz/storage/att/E6EF7938F0E854BAE520AC119FB22E8D/Prevodnik_oboru_Frascati.pdf">converter</a>)
10101 - Pure mathematics<br>10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Completed project evaluation
Provider evaluation
V - Vynikající výsledky projektu (s mezinárodním významem atd.)
Project results evaluation
Project contributed to mathematical theory of complexity of neural networks. Estimates of model complexity in dependence on dimension of input data, types and parameters of computational units, properties of approximated functions and training data werederived. Evolutionary algorithms for metalearning were designed, implemented as a software tool, and functionality and properties were verified.
Solution timeline
Realization period - beginning
May 1, 2010
Realization period - end
Dec 31, 2012
Project status
U - Finished project
Latest support payment
Feb 16, 2012
Data delivery to CEP
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data delivery code
CEP13-MSM-ME-U/01:1
Data delivery date
Jun 28, 2013
Finance
Total approved costs
540 thou. CZK
Public financial support
540 thou. CZK
Other public sources
0 thou. CZK
Non public and foreign sources
0 thou. CZK