NNeduca: A software environment to teach artificial neural networks

Artificial neural networks are an integral part of the curriculum in many undergraduate computer science programs. This paper introduces NNeduca, a simulation software system designed to teach undergraduate students the fundamental concepts of artificial neural networks. The system is written in Jav...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computer applications in engineering education 2023-09, Vol.31 (5), p.1447-1464
Hauptverfasser: Jovanović, Nenad, Stamenković, Srećko, Jovanović, Stefan
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Artificial neural networks are an integral part of the curriculum in many undergraduate computer science programs. This paper introduces NNeduca, a simulation software system designed to teach undergraduate students the fundamental concepts of artificial neural networks. The system is written in Java and aims to provide an intuitive user interface, support for research and learning activities, and the ability to expand. This tool allows students to design and train a neural network with any architecture they desire and visualize some artificial neural network theoretical concepts such as definitions, topologies, training methods, and structure. An overview of educational software systems to aid in learning the fundamental concepts of neural networks was created based on a systematic literature review. A comparison of existing simulation systems and the developed NNeduca tool was performed in this paper. The evaluation was carried out using a newly developed model for assessing the quality of selected systems using established criteria formed as a result of a thorough examination of relevant methods of evaluating educational software. The usability evaluation results show that the NNeduca tool received the highest ratings, indicating that it can significantly improve the teaching process in artificial neural network courses.
ISSN:1061-3773
1099-0542
DOI:10.1002/cae.22655