Visual and Contextual Learning for Deep Learning Education: A Unified Tool for Theory–Practice Integration
Journal of Deep Learning · 2025
DOI: 10.23917/jdl.v1i1.11556 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Deep Learning, 2025. Verfasst von Itang Enrico Pradana Mahardhika und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The rapid advancements in artificial intelligence, particularly in deep learning, demand learning methods that are not only theoretical but also applicative and intuitive. This study aims to design and develop an interactive deep learning instructional tool that integrates real-world case studies and dynamic visualizations to enhance users’ conceptual understanding and practical skills. The research employs a development methodology with a mixed-methods approach, adopting the ADDIE model and iterative formative evaluation based on Tessmer’s framework. The developed tool incorporates three primary case studies: image classification, sentiment analysis, and time-series prediction. Each case study features an interactive interface that allows users to explore data, adjust model parameters, and visualize training processes and results in real time. Formative evaluation results demonstrate the tool’s effectiveness in improving learning engagement, understanding of deep learning model mechanisms, and motivation to explore the topic further. These findings underscore the significance of experiential and visualization-based approaches in cutting-edge technology education while contributing to the development of adaptive AI-based learning media.
Zitieren
APA
Mahardhika, I. E. P., Prayitno, H. J., Indri, I., & Fitriyan, M. R. (2025). Visual and Contextual Learning for Deep Learning Education: A Unified Tool for Theory–Practice Integration. Journal of Deep Learning. https://doi.org/10.23917/jdl.v1i1.11556
Vancouver
Mahardhika IEP, Prayitno HJ, Indri I, Fitriyan MR. Visual and Contextual Learning for Deep Learning Education: A Unified Tool for Theory–Practice Integration. Journal of Deep Learning. 2025. doi:10.23917/jdl.v1i1.11556
BibTeX
@article{Mahardhika2025,
author = {Mahardhika, Itang Enrico Pradana and Prayitno, Harun Joko and Indri, Indri and Fitriyan, Muhammad Ramadhan},
title = {Visual and Contextual Learning for Deep Learning Education: A Unified Tool for Theory–Practice Integration},
journal = {Journal of Deep Learning},
year = {2025},
doi = {10.23917/jdl.v1i1.11556}
}
EUVIMED