Koceski, Saso and Koceska, Natasa and Koceva Lazarova, Limonka and Miteva, Marija and Zlatanovska, Biljana (2023) Using ChatGPT for Numerical Solution of First and Second Order Ordinary Differential Equations. In: FMNS 2023, 14-18 June 2023, Blagoevgrad, Bulgaria.
![[thumbnail of FMNS_2023_Bulgaria Chat GPT.pdf]](/style/images/fileicons/text.png) |
Text
FMNS_2023_Bulgaria Chat GPT.pdf - Presentation Download (852kB) |
|
Text
FMNS 2023 programa.pdf Download (324kB) |
Abstract
Considering the existing theories for learning or development of mathematical knowledge on specific subjects and following the latest development in the field of Artificial intelligence (AI), especially the public availability of ChatGPT, we decided to evaluate its capabilities for numerical solution of ordinary differential equations (ODE) from multiple aspects such as: Conceptual Understanding, Procedural Proficiency, Problem Solving and Application in Real-world Contexts. For the purpose of this research custom methodology based on specific indicators was developed. Obtained results suggest that ChatGPT is a promising AI tool for numerical solution of ODEs as well as for programming code generation. However, there are still some limitations and challenges when using AI for numerical solution generation, such as the need for large amounts of high-quality training data, potential biases in the algorithm, and the ability to explain how the algorithm came up with its output. This is especially valid for more complex problems.
| Item Type: | Conference or Workshop Item (Speech) |
|---|---|
| Subjects: | Natural sciences > Computer and information sciences Natural sciences > Matematics |
| Divisions: | Faculty of Computer Science |
| Depositing User: | Marija Miteva |
| Date Deposited: | 07 Sep 2023 12:02 |
| Last Modified: | 07 Sep 2023 12:02 |
| URI: | https://eprints.ugd.edu.mk/id/eprint/32144 |
Actions (login required)
 |
View Item |