About the journal

• Home page
• Contact information
• Aims and scope
• Indexing information
• Editorial policies
• ComSIS consortium
• Journal boards
• Managing board

For authors

• Information for contributors
• Paper submission
• Article submission through OJS
• Copyright transfer form
• Download section

For readers

• Forthcoming articles
• Current issue
• Archive

For reviewers

• View and review submissions

News

• Journal's Facebook page
• Calls for special issues
• New issue notification

PTB-FLA Development Paradigm Adaptation for ChatGPT

Miroslav Popovic¹, Marko Popovic², Ivan Kastelan¹, Miodrag Djukic¹ and Ilija Basicevic¹

1. University of Novi Sad, Faculty of Technical Sciences
   Trg D. Obradovica 6, 21000 Novi Sad, Serbia
   {miroslav.popovic, ivan.kastelan, miodrag.djukic, ilija.basicevic}@rt-rk.uns.ac.rs
2. 2 RT-RK Institute for Computer Based Systems, Narodnog fronta 23a,
   21000 Novi Sad, Serbia
   marko.popovic@ rt-rk.com

Abstract

The Python Testbed for Federated Learning Algorithms (PTB-FLA) is a simple Python FL framework that is targeting edge systems and is by its design easy to use by human ML&AI developers. The original PTB-FLA development paradigm intended for humans consists of the four phases (producing the sequential code, the federated code, the federated code with callbacks, and the PTB-FLA code, respectively), and hence dubbed the four-phases (development) paradigm, was validated in the case study on the logistic regression. In this paper, we adapted the original paradigm into the two new paradigms for ChatGPT, named the adapted four-phases paradigm and the adapted two-phases paradigm, respectively. In tune with its name, the latter consists of two phases (producing the sequential and the PTB-FLA code, respectively). We successfully validated both new paradigms using the same case study on logistic regression that was used for the original paradigm. The results are positive and encouraging as the resulting program codes are of better quality than the codes solely made by humans using the original paradigm.

Key words

Decentralized Intelligence, Federated Learning, Python, ChatGPT, Software Development

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS231224036P

Publication information

Volume 21, Issue 4 (September 2024)
Year of Publication: 2024
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

Available in PDF
Portable Document Format

How to cite

Popovic, M., Popovic, M., Kastelan, I., Djukic, M., Basicevic, I.: PTB-FLA Development Paradigm Adaptation for ChatGPT. Computer Science and Information Systems, Vol. 21, No. 4, 1269–1292. (2024), https://doi.org/10.2298/CSIS231224036P