A NUMERICAL SOLUTION FOR AN INITIAL VALUE PROBLEM FOR ODE USING ARTIFICIAL NEURAL NETWORK
Journal Title: Journal of Science And Arts - Year 2009, Vol 11, Issue 2
Abstract
Artificial Neural Network (ANN) proved to be good tools for functions approximation Starting from this idea the article present a method for the approximating the solution of an initial value problem for ordinary differential equation (ODE) using ANN. The performance function associated to the neural network is built in such a way that the training process to produce at the output of the network a function that satisfies the differential equation on the training set and also the initial condition.
Authors and Affiliations
Emil Lungu
Keywords
Related Articles
- EP ID EP83429
- DOI -
- Views 326
- Downloads 0
LEAD AS A TOXIC WATER CONTAMINANT – HEALTH EFFECTS AND METHODS OF ANALYSIS
Lead is heavy metal and toxic pollutants and it creates a health problem in both human and animals. Lead comes in drinking-water due to used in plumbing, fittings, solder, pipes, tetraethyl and tetramethyl used as antikn...
TRIGONOMETRICAL IDENTITIES AND INEQUALITIES
In this paper we present some new identities and inequalities in triangles and quadrilaterals, continuing the idea from [1].
AAS AND TDS MEASUREMENTS FOR WATER QUALITIES ANALYSIS
Water quality is affected by the many substances water contacts during its movement through the hydrologic cycle. Water dissolves a wide variety of minerals, nutrients, and other substances from soils, rocks, and the atm...
THE VECTOR ε ACCELERATION ALGORITHM
The purpose of this article is to make a short introduction to the vector ε acceleration algorithm and give an example of how it can be used to approximate the solution a linear system o equations.
USE OF THE MEDIAN IN THE ANALYSIS OF EXPERIMENTAL DATA
The concept of median is defined. The advantage of the median in special cases and the comparison with the classical arithmetical mean and weighted mean are presented. The case of discrepant results is analyzed. The calc...