| Autor: |
KOCESKI, SASO, KOCESKA, NATASA, LAZAROVA, LIMONKA KOCEVA, MITEVA, MARIJA, ZLATANOVSKA, BILJANA |
| Předmět: |
|
| Zdroj: |
Balkan Journal of Applied Mathematics & Informatics; 2023, Vol. 6 Issue 2, p103-114, 12p |
| Abstrakt: |
In this research we have conducted an empirical study to evaluate the capabilities of OpenAI's chat bot ChatGPT for automated software code generation and programming numerical methods for solving various types of differential equations. We have tested the ChatGPT for analytical as well as numerical solution of the first and second order ordinary differential equations. The obtained results suggest that ChatGPT is a promising AI tool for programming numerical algorithms and solving differential equations. However, there are still some limitations and challenges of using AI for numerical solution generation, related to the potential biases in the algorithm, as well as the need for a large amount of high-quality training data. However, as AI technology continues to develop, it is likely that the use of AI for programming will become more prevalent and effective in the future. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
