Approximation of Multi-parametric Functions Using The Differential Polynomial Neural Network

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27740%2F13%3A86087417" target="_blank" >RIV/61989100:27740/13:86087417 - isvavai.cz</a>

Result on the web

<a href="http://www.iaumath.com/content/7/1/33" target="_blank" >http://www.iaumath.com/content/7/1/33</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1186/2251-7456-7-33" target="_blank" >10.1186/2251-7456-7-33</a>

Result language

angličtina

Original language name

Approximation of Multi-parametric Functions Using The Differential Polynomial Neural Network

Original language description

Unknown data relations can describe a lot of complex systems through a partial differential equation solution of a multi-parametric function approximation. Common artificial neural network techniques of a pattern classification or function approximationin general are based on whole-pattern similarity relations of trained and tested data samples. It applies input variables of only absolute interval values, which may cause problems by far various training and testing data ranges. Differential polynomialneural network is a new type of neural network developed by the author, which constructs and resolves an unknown general partial differential equation, describing a system model of dependent variables. It creates a sum of fractional polynomial terms, defining partial mutual derivative changes of input variables combinations. This type of regression is based on learned generalized data relations. It might improve dynamic system models a standard time-series prediction, as the character of

Czech name

—

Czech description

—

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

IN - Informatics

OECD FORD branch

—

Project

<a href="/en/project/EE2.3.30.0016" target="_blank" >EE2.3.30.0016: Opportunities for young researchers</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2013

Confidentiality

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

Name of the periodical

Mathematical Sciences

ISSN

2251-7456

e-ISSN

—

Volume of the periodical

7

Issue of the periodical within the volume

7

Country of publishing house

DE - GERMANY

Number of pages

7

Pages from-to

1-7

UT code for WoS article

—

EID of the result in the Scopus database

—