Regression-based weight generation algorithm in neural network for solution of initial and boundary value problems

This paper introduces a new algorithm for solving ordinary differential equations (ODEs) with initial or boundary conditions. In our proposed method, the trial solution of differential equation has been used in the regression-based neural network (RBNN) model for single input and single output syste...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Neural computing & applications Ročník 25; číslo 3-4; s. 585 - 594
Hlavní autoři:	Chakraverty, S., Mall, Susmita
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	London Springer London 01.09.2014 Springer
Témata:	Applied sciences Artificial Intelligence Computational Biology/Bioinformatics Computational Science and Engineering Computer Science Computer science; control theory; systems Connectionism. Neural networks Data Mining and Knowledge Discovery Exact sciences and technology Image Processing and Computer Vision Mathematical analysis Mathematics Numerical analysis Numerical analysis. Scientific computation Ordinary differential equations Original Article Partial differential equations, initial value problems and time-dependant initial-boundary value problems Probability and Statistics in Computer Science Sciences and techniques of general use Feed-forward model Error back propagation Regression fitting Artificial neural network Differential equation Backpropagation Input output Initial condition Initial value problem Error function Minimization Regression analysis Neural network Boundary condition Modeling Weighted graph Backpropagation algorithm First order equation Boundary value problem Feedforward neural nets Regression model Feedforward Growth of error Mathematical programming
ISSN:	0941-0643, 1433-3058
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!