DOI

The paper discusses the connection of Taylor maps and polynomial neural networks (PNN) for numerical solving of the ordinary differential equations (ODEs). Having the system of ODEs, it is possible to calculate weights of PNN that simulates the dynamics of these equations. It is shown that proposed PNN architecture can provide better accuracy with less computational time in comparison with traditional numerical solvers. Moreover, neural network derived from the ODEs can be used for simulation of system dynamics with different initial conditions, but without training procedure. Besides, if the equations are unknown, the weights of the PNN can be fitted in a data-driven way. In the paper, we describe the connection of PNN with differential equations theoretically along with the examples for both dynamics simulation and learning with data.
Язык оригиналаанглийский
Название основной публикацииECAI 2020 - 24th European Conference on Artificial Intelligence, including 10th Conference on Prestigious Applications of Artificial Intelligence, PAIS 2020 - Proceedings
РедакторыGiuseppe De Giacomo, Alejandro Catala, Bistra Dilkina, Michela Milano, Senen Barro, Alberto Bugarin, Jerome Lang
ИздательIOS Press
Страницы1230-1237
Число страниц8
ISBN (электронное издание)9781643681009
ISBN (печатное издание)978-1-64368-100-9
DOI
СостояниеОпубликовано - 24 авг 2020
Событие24th European Conference on Artificial Intelligence - Сантьяго де Компостела, Испания
Продолжительность: 29 авг 20208 сен 2020
Номер конференции: 24

Серия публикаций

НазваниеFrontiers in Artificial Intelligence and Applications
Том325
ISSN (печатное издание)0922-6389

конференция

конференция24th European Conference on Artificial Intelligence
Сокращенное названиеECAI
Страна/TерриторияИспания
ГородСантьяго де Компостела
Период29/08/208/09/20

    Предметные области Scopus

  • Искусственный интеллект

ID: 62094035