A substitution of the general partial differential equation with extended polynomial networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F16%3A86099062" target="_blank" >RIV/61989100:27240/16:86099062 - isvavai.cz</a>

Výsledek na webu

<a href="http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7727833" target="_blank" >http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7727833</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IJCNN.2016.7727833" target="_blank" >10.1109/IJCNN.2016.7727833</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A substitution of the general partial differential equation with extended polynomial networks

Popis výsledku v původním jazyce

General partial differential equations, which can describe any complex functions, may be solved by an adapted method of the similarity analysis that models polynomial data relations of discrete observations. The proposed new differential polynomial networks define and substitute for a selective form of the general partial differential equation using fraction derivative units to model an unknown system or pattern. Convergent series of relative derivative substitution terms, produced in all network layers, describe the partial derivative changes of some combinations of input variables to generalize elementary polynomial data relations. The general differential equation is decomposed into polynomial network backward structure, which defines simple and composite sum derivative terms in respect of previous layers variables. The proposed method enables to form more complex and varied derivative selective series models than standard soft-computing techniques. The sigmoidal function, commonly employed as an activation function in artificial neurons, may improve the abilities of the polynomial networks and substituting derivative terms to approximate complicated periodic multi-variable or time-series functions in a system model. (C) 2016 IEEE.

Název v anglickém jazyce

A substitution of the general partial differential equation with extended polynomial networks

Popis výsledku anglicky

General partial differential equations, which can describe any complex functions, may be solved by an adapted method of the similarity analysis that models polynomial data relations of discrete observations. The proposed new differential polynomial networks define and substitute for a selective form of the general partial differential equation using fraction derivative units to model an unknown system or pattern. Convergent series of relative derivative substitution terms, produced in all network layers, describe the partial derivative changes of some combinations of input variables to generalize elementary polynomial data relations. The general differential equation is decomposed into polynomial network backward structure, which defines simple and composite sum derivative terms in respect of previous layers variables. The proposed method enables to form more complex and varied derivative selective series models than standard soft-computing techniques. The sigmoidal function, commonly employed as an activation function in artificial neurons, may improve the abilities of the polynomial networks and substituting derivative terms to approximate complicated periodic multi-variable or time-series functions in a system model. (C) 2016 IEEE.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2016

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the International Joint Conference on Neural Networks

ISBN

978-1-5090-0619-9

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

4819-4826

Název nakladatele

Institute of Electrical and Electronics Engineers

Místo vydání

New York

Místo konání akce

Vancouver

Datum konání akce

24. 7. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—